capture_feedback

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

The description claims feedback is 'logged' and 'returned', implying a write operation, while annotations set readOnlyHint=true. This is a direct contradiction. Beyond that, the description does not disclose auth needs, rate limits, or other behavioral traits.

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 concise, consisting of two short sentences. It is front-loaded with the main purpose. However, it could be slightly more structured.

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 the tool's complexity (13 parameters, nested objects, no output schema, low schema coverage), the description is incomplete. It does not explain many optional parameters, return values, or how the tool integrates with other feedback utilities.

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 low (38%), and many parameters (e.g., whatWentWrong, whatToChange, whatWorked, tags, skill, rubricScores, guardrails) lack descriptions in both schema and the tool description. The description only mentions 'up/down signal' and 'one line of why', adding little value beyond the schema.

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. It also hints at handling of vague feedback, distinguishing it from siblings like capture_memory_feedback. However, it does not explicitly differentiate from append_feedback_context or other feedback tools.

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 gives a brief context ('Capture an up/down signal plus one line of why') and specifies behavior for vague feedback (logged and returned with clarification prompt). However, it does not explicitly state when to use this tool vs. siblings like append_feedback_context or capture_memory_feedback.

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