label_finding

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

The description discloses key behaviors: 'Append-only: existing records are never rewritten' and 'accept-verdict precedents suppress matching findings in future audit_taste runs.' Annotations include destructiveHint=true, which aligns with append-only (adds data, doesn't overwrite). No contradiction.

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 that pack purpose, usage, and key behaviors without any fluff. Every sentence earns its place.

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?

With 7 parameters and no output schema, the description covers purpose, usage, behavioral notes, and parameter hints. It's comprehensive enough for an agent to use correctly, though a brief example could further aid understanding.

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%, but the description adds useful context beyond schema: for 'wrong', it advises 'use a verbatim snippet so accept-suppression can match it.' For 'verdict', it explains the difference between accept and revise/reject. This enhances understanding.

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's action: 'Append a labeled precedent to a taste profile's corpus'. It distinguishes from siblings by specifying the context of audit_taste findings or labeling new wrong→right examples.

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?

Explicit usage context is provided: 'Use when a human accepts/revises/rejects an audit_taste finding or labels a new wrong→right example.' It also notes it's append-only, but doesn't explicitly mention when not to use or list alternatives.

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