prompteye-mcp

Official

by PROMPTEYE-SP-Z-O-O

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Read the assistants' answers

get_prompt_answers

Read-only

The individual assistant answers behind the metrics, newest first — the answer text, whether the brand was named and at which position, and the sources cited.

Instructions

The individual assistant answers behind the metrics, newest first — the answer text, whether the brand was named and at which position, and the sources cited. Call this when a figure needs checking: it is where a number is verified when someone asks why it moved.

Pass resultId with one of the sourceResultIds from get_brand_analysis_run to verify the evidence for a gap; the date range is then ignored. Pass promptId with model to read how a given assistant answers a prompt. brand narrows to the answers that named the brand (named) or did not (missing), and search to the answers containing a phrase in the answer, prompt, brands or sources.

Without a date range the last 30 days are read; a range is at most one year. A page ends on a whole collection run, so it can hold slightly more than limit answers. Pass nextCursor back as cursor to read the next page.

Input Schema

Name	Required	Description
`brand`	No	named = only answers that named the brand, missing = only those that did not.
`limit`	No	How many answers to aim for, at most 50. Defaults to 25.
`model`	No	Report on this assistant alone instead of all of them.
`cursor`	No	The nextCursor of the previous page, passed back unchanged. Omit it to start from the newest answer.
`search`	No	Only the answers containing this phrase in the answer text, prompt, brands or sources.
`endDate`	No	Last day to report on, inclusive. Defaults to today, and must be within 366 days of startDate.
`promptId`	No	Only the answers to this prompt.
`resultId`	No	Only the answers of this one collection run, a sourceResultIds entry of a brand analysis.
`projectId`	Yes	The project to work on — its id from list_projects. Required on every call, so that parallel conversations never read or write each other's project.
`startDate`	No	First day to report on, inclusive. Defaults to 30 days before today.

Output Schema

Name	Required	Description	Default
`data`	Yes
`nextCursor`	Yes	Pass as cursor to read the next page. null = this was the last page.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.28Oct 23, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the substantive behavior an agent needs: ordering (newest first), default window of 30 days, a one-year cap, that `resultId` causes the date range to be ignored, and that page boundaries fall on whole collection runs so a page may exceed `limit`. It also explains cursor round-tripping, none of which is in the annotations.

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?

Well front-loaded: what it returns, then when to call it, then parameter modes, then defaults and pagination. Every sentence carries information, but the second paragraph is a dense run of clauses that takes re-reading; a short list would scan faster for a 10-parameter tool.

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?

An output schema exists, so return-value explanation is not required, yet the description still sketches the record shape. Combined with the stated defaults, cap, pagination and filter interactions, an agent has everything needed to call this correctly on the first try.

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

Parameters5/5

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

Schema coverage is already 100%, so the bar is higher, and the description clears it by documenting cross-parameter interactions the schema cannot express: resultId overriding the date range, promptId requiring/being paired with model, and what `brand` and `search` actually filter over. This is real added meaning rather than restatement of enum values.

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 opening sentence names the resource precisely (individual assistant answers behind the metrics) and enumerates what each record contains: answer text, brand named/position, sources cited. It is immediately distinguishable from get_brand_analysis_run, which returns the aggregated metrics rather than the underlying answers.

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

Usage Guidelines5/5

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

Explicit trigger is given ('Call this when a figure needs checking'), plus a named alternative in the sibling set: pass `resultId` from get_brand_analysis_run's sourceResultIds to verify evidence for a gap. It also states which parameter combinations serve which question (promptId+model, brand, search), so the agent knows not just when to call but which mode to use.

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

Deploy Server