Skip to main content
Glama
competlab

competlab-mcp-server

by competlab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

get_ai_visibility_trend

Read-only

Track how AI model answers moved over a chosen window: see which companies are named more or less often and whether your brand's standing changed.

Instructions

How the AI models' market MOVED over a window: who is recommended more or less often, and whether the customer's standing changed. A move is a change in how the AI models answered, never a fact about a third party's business. item.companies: the customer (isOwn), every tracked competitor (isTracked) and up to 3 untracked companies, ordered by presence on the latest map (ties stay ties); one with no reading takes no row. now is the latest map and pools its own checksAnalysed checks: never the latest check alone (get_ai_visibility_history limit=1 has that). start is the earliest map in the window. presenceChange is in points of share, rankChange (places, positive = climbed) and scoreChange.

  • Call presenceChange a rise or a fall ONLY when presenceChangeSeparable is true. Otherwise give both shares and say the ranges overlap.

  • A reading is presence.answersNaming of presence.answersReceived, never of queries sent, with a 95% range and a zone. Overlapping ranges are not a settled order. Say the zone's condition ('named in under a tenth of answers'), never 'irrelevant' or 'tail'.

  • start null: 'one reading, no movement to compare', never zero change.

  • Read enginesBacking before saying a company is named across the market. An EMPTY enginesBacking means no model named it on the latest map.

  • score is WHERE a brand lands when named (top 5 only), never who is ahead: standing rests on presence. null means not measured, never zero; a measured zero ships as 0. Except rank and rankChange: null on a company no answer named is a measured absence. Say 'not named', never a place or a fall. item.events: standingChanges are the customer's alerts (a standing held two checks): 'your standing moved from X to Y on '. incompleteCycles: report expectedAnswers minus measuredAnswers and absentAnswers apart, never as a fraction. promptsLastChangedAt: the questions changed then, so a move across it is not the market moving. item.window: quote answers and checks, never days.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateToNoEnd of the window, ISO-8601 (e.g., 2026-03-15).
detailNo`series` adds each company's share check by check (at most 12 evenly spaced points). Omit unless the shape between the ends matters: the rows already carry the reading now, the reading at the start, and the difference. A null presence on a series point means the model returned no usable answer in that check's window.
dateFromNoStart of the window, ISO-8601 (e.g., 2026-01-01). Omit for the whole history. The window reads at most the newest 200 published checks, readings and events.incompleteCycles alike, so on a long history set dateFrom and dateTo to keep both on one span.
providerNoRead one AI model's own slice of every map; omit for every model at once. Under one model, rank and score are null on every reading and enginesBacking is left off the rows, because one model's slice cannot answer them; never read that as 'no model named them'. A company with no measured reading for that model in the window is left out, and window.answersReceived is null when that model had no usable answer in the latest window.
projectIdYesProject ID (from list_projects)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv4.0.1
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedInput schema / properties / dateFrom / description
      Previous value: -"Start of the window, ISO-8601 (e.g., 2026-01-01). Omit for the whole history (the newest 200 published checks)."New value: +"Start of the window, ISO-8601 (e.g., 2026-01-01). Omit for the whole history. The window reads at most the newest 200 published checks, readings and events.incompleteCycles alike, so on a long history set dateFrom and dateTo to keep both on one span."
    • changedInput schema / properties / detail / description
      Previous value: -"`series` adds each company's share check by check (at most 12 evenly spaced points). Omit unless the shape between the ends matters — the rows already carry the reading now, the reading at the start, and the difference."New value: +"`series` adds each company's share check by check (at most 12 evenly spaced points). Omit unless the shape between the ends matters: the rows already carry the reading now, the reading at the start, and the difference. A null presence on a series point means the model returned no usable answer in that check's window."
    • changedInput schema / properties / provider / description
      Previous value: -"Read one AI model's own slice of every map. Omit for every model at once. Under one model, rank and score are null on every reading and enginesBacking is left off the rows — they exist only across every model; never read that as 'no model named them'."New value: +"Read one AI model's own slice of every map; omit for every model at once. Under one model, rank and score are null on every reading and enginesBacking is left off the rows, because one model's slice cannot answer them; never read that as 'no model named them'. A company with no measured reading for that model in the window is left out, and window.answersReceived is null when that model had no usable answer in the latest window."
  2. Changed5 schema fields changedv3.0.0
    • changedInput schema / properties / dateFrom / description
      Previous value: -"Start date in ISO-8601 format (e.g., 2026-01-01)"New value: +"Start of the window, ISO-8601 (e.g., 2026-01-01). Omit for the whole history (the newest 200 published checks)."
    • changedInput schema / properties / dateTo / description
      Previous value: -"End date in ISO-8601 format (e.g., 2026-03-15)"New value: +"End of the window, ISO-8601 (e.g., 2026-03-15)."
    • addedInput schema / properties / detail
      Added value: +{
+  "const": "series",
+  "description": "`series` adds each company's share check by check (at most 12 evenly spaced points). Omit unless the shape between the ends matters — the rows already carry the reading now, the reading at the start, and the difference.",
+  "type": "string"
+}
    • changedInput schema / properties / provider / description
      Previous value: -"Filter by LLM provider. Omit for aggregate view across all providers"New value: +"Read one AI model's own slice of every map. Omit for every model at once. Under one model, rank and score are null on every reading and enginesBacking is left off the rows — they exist only across every model; never read that as 'no model named them'."
    • changedInput schema / properties / provider / enum
      Previous value: -[
-  "openai",
-  "claude",
-  "gemini"
-]New value: +[
+  "openai",
+  "claude",
+  "gemini",
+  "perplexity",
+  "google_ai_overviews"
+]
  3. First observedv1.0.0

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds extensive behavioral context beyond that: it explains what 'move' means, how nulls are treated, when to call a rise or fall (presenceChangeSeparable), what enginesBacking implies, and how to report incomplete cycles. These rules are critical for correct interpretation and are not available in the annotations or schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but structured with bullet points and front-loads the core purpose. Given the tool's complexity and the absence of an output schema, most sentences earn their place by specifying required interpretation rules. It is dense but not redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must fully explain return values and semantics. It covers field semantics (presenceChange, rankChange, scoreChange), event handling (standingChanges, incompleteCycles, promptsLastChangedAt), window quoting, null treatment, and enginesBacking. This is comprehensive for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters are thoroughly documented in the schema itself. The description adds no parameter-specific syntax or format details beyond what the schema provides; it focuses entirely on output interpretation. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific purpose: showing how the AI models' market moved over a window, who is recommended more or less, and whether the customer's standing changed. It distinguishes itself from get_ai_visibility_history by noting that the latter with limit=1 provides the latest check alone. An agent can identify the tool's scope without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for comparing movement across a time window, but it does not explicitly state when to use it versus alternatives like the dashboard or history endpoints. A single alternative is mentioned in passing (get_ai_visibility_history limit=1), but there is no general when-to-use or when-not-to-use guidance. The heavy interpretation rules are useful but not usage selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools