evaluate_policy

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

Annotations are missing, so description carries the burden. It explains return format (allowed:true/false plus individual checks) but does not disclose whether the tool modifies state, requires authentication, or has rate limits. No contradictions, but adds moderate value beyond annotations.

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 policy example. Extremely concise, no filler. Front-loaded with core purpose, then example clarifies usage. 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?

Given moderate complexity (4 parameters, nested object, no output schema), the description is complete enough: states purpose, return format, and gives example. No explanation of individual parameters beyond the example, but the schema and example together suffice.

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 0%, so description must compensate. It does not detail parameters but provides a comprehensive example policy that covers most parameter fields intuitively. For a nested object with 5 sub-fields, the example aids understanding significantly.

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?

Description clearly states the tool checks trust policy, returns allowed:true/false with details, and provides a real example. This distinguishes it from siblings like 'recommend' or 'list_trusted'.

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 includes a use-case example for gating decisions about server use for financial data, but does not explicitly mention when not to use this tool vs alternatives like check_trust.

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