3RD

Get owned-citation share per provider for a brand over a date range (default last 30 days). Provide fromDate/toDate (YYYY-MM-DD) to scope the window. Matches the dashboard Attribution by provider card.

get_attribution_share

Get the DETAILED per-source citation list for a brand — the Citations Top Sources view. Each cited URL with its owned/earned kind, citation count, share, the prompts/providers/topics/competitors behind it, and brand-mention status. Use when the question is WHICH sources cite the brand (get_citations returns only the owned/earned share). Also the tool for 'which URLs/pages from domain X are cited' and 'which sources drive our must-win prompts': domain keeps only URLs on that host (or its subdomains) and promptType restricts to prompts of one category (must-win / core / foundation) — the answer is the per-URL list with the prompts behind each URL. Optional fromDate/toDate (YYYY-MM-DD) scope the window; kind filters owned/earned/paid. topicId (or topicIds for several) scopes to a topic's prompts and marketId / country (ISO alpha-3, e.g. DNK) to one market — these narrow WHAT IS COUNTED, so citations and share are that topic/market's, not the source's brand-wide totals, and match the dashboard with the same filters applied. Topic ids come from get_topic_mentions, market ids from list_markets_audiences. Paginated: limit is the page size (default 50, max 200) and page (1-based) selects the page; the response includes total and totalPages — request further pages to walk the full source list. High-volume brands: aggregating a wide window in one request can exceed the time budget; when it does the response comes back with timedOut:true, an empty sources array, and a chunkHint — narrow the window (e.g. one week at a time) and/or pass a single marketId, then page through each smaller slice. gap:true keeps only gap sources — pages that mention at least one tracked competitor while a check of the page's content found the brand absent (pages not yet checked are left out), off the brand's own site; every row then has brandMentioned false and a non-empty competitorsMentioned. The filter runs before pagination, so total counts gap sources only, while share stays a share of all the brand's citations. groupBy:'domain' returns domains instead of sources: per domain the citations, share, previousCitations, urlCount, brandMentionedUrlCount and the competitors mentioned (with how many of its URLs mention each), ranked by citations over the whole source list; limit/page then page through domains, and the domain citations add up to totalCitations. Combine gap and groupBy for a per-domain gap list.

get_citation_sources

Get the brand-vs-competitor ranking by visibility score (brand + competitors sorted, each with score and rank, plus the brand own rank). Optional fromDate/toDate (YYYY-MM-DD) scope the window; without them this reports the last 30 days. Returns the SAME ranking as the dashboard Competitor rank card / Leaderboard (prompt-averaged visibility); report it verbatim.

get_competitor_ranking

Get the brand's content recommendations — the same list, numbers and order as the Content page in the app (default view: every prompt, highest opportunity first). Per prompt: whether the brand's own pages cover it (coverage %, matching-page count, opportunity score), the recommended action (optimize an existing page, create a new one, or defend), the recommended content type and target URL, and the brand's visibility and citation share for that prompt. Pass topicId to see one topic only. Coverage is a standing state of the brand's pages, not a windowed metric, so this takes no date range — do not report it under another tool's period.

get_content_gaps

Fetch one brand's stored record as a document body — url, siteUrl (the brand's main tracked website), name, products, competitors and markets — by an id `search` returned. This is the fetch half of the ChatGPT connector contract, and the corpus it addresses is the brands you can access, not citations, monitored pages or answer text (use get_citations, list_monitored_pages or get_prompt_responses for those). Pass `id`; `documentId` is accepted as an alias for the same value, and exactly one of the two is required.

fetch

Get the brand KPI summary — visibility score, sentiment distribution, citation share (owned/earned/total) and tasks. Optional fromDate/toDate (YYYY-MM-DD) scope the window; without them this reports the last 30 days. Its visibility score is the SAME number as Total visibility on the Overview page (prompt-averaged, honouring the branded-prompt toggle); report every figure verbatim. Citation share, sentiment and tasks are not in the Overview top row, so never say they are. `status` is the direction versus comparisonPeriod (the preceding equal-length window) — up/down/neutral, or unknown when there is nothing comparable, in which case claim no direction; `level` is only the 50% threshold on the absolute score, never a trend.

get_highlights

List all brands accessible to the authenticated user. Each brand carries isInternal — true when it belongs to a 3RD-internal/test workspace rather than a customer — plus orgId and orgName, so you have a real orgId to pass to add_brand when the caller has more than one organisation.

list_brands

List tracked competitors for a brand, each with its `id`, `name`, `url`, `aliases` and `countryCodes`. Pass the id to update_competitor to edit one.

list_competitors

The recommended next tasks for a brand — the same cards, in the same order, as the Recommended rail on Task Management. These are NOT in the plan yet; the tasks already in the plan are get_playbook. Use this when asked what to do next. A suggestion the team dismissed never appears, and on a plan with a monthly recommended-tasks quota only the suggestions already revealed this month are returned (`quota.heldBack` counts the rest; reading never spends the quota). `existingTaskId` is set when the suggestion is an archived task the engine re-offers, and `taskUrl` then opens that task in the app. Optional `marketId` (UUID) scopes the list to one market; `limit` caps it (default and max 50). Present these as suggestions the team can add, never as planned work.

list_suggested_tasks

Get the opportunity radar for a brand — the same 5 canonical drivers (content coverage, content quality, crawlability, authority, outreach) the Diagnostics page shows, each scored 0-100, plus an overall score. Each dimension carries `dataAvailable`: when false the driver had no scorable rows and its 0 means "not measured", NOT a low score — report it as unmeasured and never call it the brand’s weakness. `overallScore` averages only the measured axes. Optional `marketId` (UUID) scopes every driver to a single market. BREAKING CHANGE from the prior version of this tool: it no longer returns the bespoke Visibility/Ranking/Sentiment/Citations/Crawlability axes, and there is no `days` window argument — only 2 of the 5 canonical drivers (authority, outreach) are windowed at all, so a single window spanning all axes never matched their real semantics.

get_opportunity_radar