Submit feedback about the API: missing features, issues, improvements. Rate limit: 5 per hour.
| Name | Required | Description | Default |
|---|---|---|---|
| context | No | Any JSON, max 4 KB | |
| endpoint | No | e.g. /v2/candidates | |
| issue_type | No | ||
| description | Yes | Max 2000 chars | |
| suggested_improvement | No | Max 2000 chars |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / context / additionalPropertiesRemoved value: -{}Input schema / properties / context / descriptionPrevious value: -"Arbitrary context object (max 4KB JSON)"New value: +"Any JSON, max 4 KB"Input schema / properties / description / descriptionPrevious value: -"Description of the issue or feedback (max 2000 chars)"New value: +"Max 2000 chars"Input schema / properties / endpoint / descriptionPrevious value: -"The API endpoint this feedback relates to, e.g. /v2/candidates"New value: +"e.g. /v2/candidates"Input schema / properties / issue_type / descriptionRemoved value: -"Category of the issue"Input schema / properties / suggested_improvement / descriptionPrevious value: -"Suggested solution or improvement (max 2000 chars)"New value: +"Max 2000 chars"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only indicate non-read-only status (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds a valuable rate limit ('5 per hour') and implies a write operation. It does not describe return behavior or side effects, but the rate limit is substantive extra context beyond annotations.
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, no fluff. The purpose is stated first, followed by the rate limit constraint. Every word earns its place, and the structure is easy to parse.
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 simple feedback submission tool with one required parameter and no output schema, the description covers the core purpose and a key constraint (rate limit). It does not state expected response or confirmation, but that is not critical for an agent to call it correctly. It feels complete enough for its simplicity.
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 coverage is 80% with all parameters except issue_type having descriptions. The description adds no parameter-specific meaning, relying on the schema's existing descriptions. The undocumented issue_type has a self-explanatory enum, so the baseline 3 is appropriate; the description does not compensate further.
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 clear verb ('Submit feedback') and resource ('the API'), with specific types of feedback (missing features, issues, improvements). It is unambiguous and distinguishes this tool as the sole feedback mechanism among many CRUD and list tools, so no sibling differentiation is needed.
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?
The description provides clear context for when to use this tool: to report missing features, issues, or improvements. There are no exclusions or alternatives, but since this is a unique feedback tool, the guidance is sufficient. It lacks explicit 'when-not-to-use' but that's not critical here.
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.