FREE: tell the operator what was missing or wrong (a route or tool you expected, a symbol without data, a confusing parameter). Read by a human; it decides the next routes.
| Name | Required | Description | Default |
|---|---|---|---|
| route | No | Route or tool it is about (optional) | |
| rating | No | Optional 1-5 rating of the route or tool | |
| message | No | Anything else, up to 1000 characters | |
| missing | No | What you needed and did not find |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds genuinely new context: submissions are human-reviewed and influence 'the next routes,' and it is free. It does not say anything about latency, retention, or whether feedback is swallowed silently, but that is beyond the annotations' scope.
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?
Two sentences, zero filler, with the incentive ('FREE') and the action front-loaded and the audience/feedback loop trailing. Every clause 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?
For a zero-required-parameter, read-only feedback sink with no output schema, the definition covers purpose, audience, and what content belongs in it. The only gap is what an agent should expect after submitting (any acknowledgment or response), which is minor.
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 100%, so the four parameters are already documented in the schema and the baseline is 3. The examples in the description loosely map to 'missing', 'route', and 'message', but they do not add syntax, format, or precedence information beyond what the schema already provides.
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?
The description states a specific verb and resource — tell the operator what was missing or wrong — and gives concrete examples (expected route/tool, symbol without data, confusing parameter). It is unmistakable from the market/decision siblings, which all serve data retrieval rather than feedback capture.
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?
It clearly frames the three situations that justify a submission (missing route/tool, missing data, confusing parameter) and notes the audience ('read by a human'). It stops short of saying when not to use it or what happens after review, so it is context-rich but not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.