label_finding

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

The description adds behavioral context beyond annotations: it is append-only, existing records are never rewritten, and accept verdicts suppress matching findings in later audit_taste runs. This gives the agent important side-effect information that the annotations alone do not express.

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 compact and well-structured: it names the core action first, gives a concrete usage condition, and then spells out the most important behavioral consequences. There is no filler or unnecessary repetition.

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 mutation-like tool with 7 parameters and no output schema, the description covers the action, trigger context, important parameter nuances, and side effects. It does not describe expected return values, but that is less critical without an output schema, and the core execution context is complete enough for an agent.

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 100%, so the baseline is 3. The description adds valuable semantics for key parameters: wrong should be a verbatim snippet for suppression matching, and verdict meanings are clarified (accept suppresses, revise/reject confirm wrong). This goes beyond the schema's generic field descriptions.

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 action and resource: append a labeled precedent/verdict to a taste profile's corpus. It identifies the basic growth-loop function clearly, but does not explicitly differentiate itself from siblings like record_taste_decisions or audit_taste, relying more on the 'when to use' phrase.

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 explicitly says to use the tool when a human accepts, revises, or rejects an audit_taste finding, or labels a new wrong→right example. This is strong guidance, but it does not mention when not to use the tool or name alternative tools for other scenarios.

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