record_feedback

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

No annotations are present, so the description carries the disclosure burden. It clearly states local-only behavior, no network access, and persistence as memory for future recommendations. It does not detail duplicate handling or exact output, but the core behavioral safety profile is explicit.

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 plus a parenthetical, all information-dense: purpose, key constraint, and routing note. No filler or repeated schema content.

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 simple two-action tool, the description plus full schema coverage gives an agent enough to select and invoke it. It delivers key context (local-only, no network, legacy alias) and the response_format parameter hints at output shapes. It could add a sentence on return values or duplicate behavior, but nothing blocks correct use.

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?

All six parameters have descriptions in the schema (100% coverage), so the baseline applies. The description mentions the rating enum values and the record/list actions, but adds no new parameter-level semantics beyond what the schema already specifies.

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 explicitly states the tool records or lists local-only taste verdicts, enumerates the valid verdict values, and notes it never touches the network. This provides a concrete verb-resource pair and distinguishes it from network-based statsfm siblings.

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 says 'Never touches the network' and 'memory for future recommendations', establishing when to use this local tool. The parenthetical explicitly names statsfm_record_feedback as the canonical alternative and instructs the agent to prefer it, giving a clear when-not-to-use rule.

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