trw_agent_work_evidence

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

No annotations are provided, so the description must carry the burden. It mentions 'privacy-safe' and 'schema-valid', implying data sanitization and standardized output. However, it does not disclose permissions, side effects, or what happens if run_path is null. More details on behavioral traits would be beneficial.

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 long, with the purpose front-loaded and usage guidelines in the second sentence. Every word adds value with no wasted text.

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 no output schema, the description could explain the return structure (e.g., 'returns a JSON object conforming to AgentWorkEvidence v1'). It also omits clarification on default behavior when run_path is not provided. For a tool with three optional parameters, these gaps reduce completeness.

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?

The input schema provides 100% coverage with descriptions for all three parameters. The description adds no extra semantic meaning beyond what the schema already offers, so a baseline score of 3 is appropriate.

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 verb 'Export' and the resource 'privacy-safe AgentWorkEvidence' for a TRW run. It distinguishes from siblings by noting it avoids scraping run internals, and among siblings like trw_validate_agent_work_evidence, the purpose is unique.

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 lists who should use it (judge, eval harness, reviewer, knowledge-graph importer) and what alternative to avoid (scraping run internals). While it does not enumerate sibling tools as alternatives, the provided context is sufficient for most use cases.

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