Searcherries: AI Visibility & SEO

Get AI Answers

get-ai-answers

Read-onlyIdempotent

Stored AI answers to the tracked customer questions, one row per check per platform, joined with their answer insights: prominence of the brand (0 not named, 1 in passing, 2 one of the options, 3 top recommendation), on-topic and names-brands probabilities, sentiment, drawback flag, evidence quote, cited URLs and the web searches the platform ran. Filter by prompt_id, platform, date range, prominence_max (1 = answers where the brand is absent or only in passing, i.e. gaps) or only_flagged (negative, drawback or off-topic). Answer text is excluded by default; set include_answer_text=true for at most 20 rows, capped by max_answer_chars.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>"
    },
    "name": "get-ai-answers"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Rows per page, 1-100. Default 25.
`since`	No	First check date to include, YYYY-MM-DD.
`until`	No	Last check date to include, YYYY-MM-DD.
`offset`	No	Rows to skip. Use with has_more.
`period`	No	Report period anchored to the latest check. Default last_30_days. Ignored when since/until are given.
`platform`	No	Restrict to one AI platform.
`market_id`	No	Projects with several markets (country + language): narrow to one market, id from the markets list of list-projects or get-project-summary. Default: every market combined.
`prompt_id`	No	Restrict to one customer question (id from ai_visibility.prompts).
`project_id`	Yes	The AI Visibility project ID returned by list-projects.
`only_flagged`	No	Only answers judged negative, with a drawback, or off topic.
`prominence_max`	No	Keep answers whose brand prominence is at most this level (0-3). Use 1 to find the gaps.
`max_answer_chars`	No	Characters of answer text per row when included, 200-20000. Default 1500.
`include_answer_text`	No	Include the stored answer text (limit capped at 20).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

addedInput schema / properties / market_id

Added value: +{
+  "description": "Projects with several markets (country + language): narrow to one market, id from the markets list of list-projects or get-project-summary. Default: every market combined.",
+  "type": "integer"
+}

First observedSep 30, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely non-obvious behavior: answer text is excluded by default, inclusion caps the result at 20 rows, and per-row text is bounded by max_answer_chars. It could still say more about ordering or the has_more pagination contract.

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?

Front-loaded with the resource and grain, then the returned fields, then filters, then the answer-text caveat — a logical order. It is a dense single paragraph, and the prominence scale partially duplicates the schema, so it is slightly over-packed but no sentence is truly wasted.

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?

For a 13-parameter read tool with no output schema, the description enumerates the returned insight fields and discloses the default-suppressed answer text with its caps. An agent has enough to call it and anticipate the response without further documentation.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns more by defining the prominence scale (0 not named through 3 top recommendation) and interpreting prominence_max=1 as the gaps query, plus spelling out what only_flagged means. This adds meaning beyond the schema's short field blurbs.

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

Purpose4/5

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

States a specific verb and resource ('Stored AI answers to the tracked customer questions') and pins down the grain ('one row per check per platform, joined with their answer insights'). It is clear what data is returned, though it never names a sibling tool such as get-project-summary to sharpen the boundary.

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

Usage Guidelines4/5

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

Gives concrete usage conditions for its filters: prominence_max=1 'to find the gaps', only_flagged for 'negative, drawback or off-topic', include_answer_text for full text. This is real when-to-use guidance, but it stops short of stating when to prefer this tool over get-project-summary or get-citations.

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

All Searcherries: AI Visibility & SEO tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.