Capture Feedback

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

The description reveals that feedback is logged and vague signals return a clarification prompt, but it contradicts the annotations which set readOnlyHint=true. The tool claims to write (capture/log), yet annotations say read-only. This is a serious inconsistency.

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?

The description is two sentences (25 words), front-loaded with the core action, and contains no waste. Every sentence earns its place by stating the action and key behavior for vague feedback.

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?

Given 13 parameters, no output schema, and low schema coverage, the description is far too sparse. It doesn't explain the purpose of key parameters like failureType, whatWentWrong, etc., nor how the tool fits into the broader feedback system.

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?

With only 38% schema description coverage, the description should compensate for the many undocumented parameters, but it only mentions 'signal' and 'context'. It adds no additional meaning for the other 11 parameters beyond what the schema 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 clearly states the tool captures an up/down signal plus a reason, specifies the signal types, and distinguishes from memory promotion. It uses a specific verb ('capture') and resource ('feedback signal'), and the mention of 'instead of memory promotion' hints at sibling differentiation.

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 implies usage for simple feedback signals and mentions that vague feedback is logged and returned with a clarification prompt, indicating when not to promote to memory. However, it lacks explicit when-not-to-use or direct comparison with sibling tools like capture_memory_feedback.

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