Report a wrongly analysed AI answer

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

Annotations already declare this is not read-only, not destructive, not idempotent. The description adds the meaningful behavior that submitting creates a review request for Mencoro, which is real side-effect context beyond the annotations. However it says nothing about permissions, whether repeat reports are deduplicated/queued, or what the caller gets back on success or failure of the ID chain.

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

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

Three tight sentences with zero filler: purpose and outcome first, then the parameter essentials, then where to find the ids. Everything is front-loaded and each sentence earns its place.

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

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

There is no output schema, so the description should convey the observable result of the call; it only implies an out-of-band human review and never says what the caller receives or how to tell success from failure. For a mutation tool with five required ID params at 0% schema coverage, that leaves meaningful gaps.

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

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

Schema description coverage is 0%, so the description must carry parameter meaning, and it does explain the two semantically non-obvious params: 'type' (enum values restated in prose) and 'comment' (says what is wrong, 1000-char cap unmentioned). The four ID parameters and 'requestId' are entirely unexplained, including the fact that trackedQueryId/projectId/organizationId must be consistent with the aiResponseId.

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

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

States a specific verb and resource: 'Flag a captured AI answer whose analysis is wrong ... so Mencoro reviews it.' It further scopes the most common case ('a brand or competitor mention that was missed'), which distinguishes it from read-only siblings like get_mention_samples or list_ai_responses.

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

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

Gives concrete operating instructions: pick type 'missed_mention' or 'other', put the explanation in 'comment', and obtain the needed ids from list_ai_responses. That is a clear when/how-to-use path with an explicit alternative tool for id lookup. It lacks any when-not guidance (e.g. don't report a mention that was never expected, or duplicates).

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