Verify declared evidence

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the five possible outcome states (verified-within-scope, contradicted, stale, inconclusive, unsupported) and the per-statement scope of verification, which is exactly what an agent needs to interpret results.

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 dense sentences with zero filler, front-loaded on what is evaluated and where. The enumerated state list is slightly packed but each item earns its place by telling the agent what outcomes to expect.

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 no output schema, the description usefully enumerates the return states so the agent can interpret results, and the single optional parameter is fully covered by the schema. Missing only the explicit relationship to the sibling verify tool.

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?

Only one optional parameter with 100% schema description coverage, so the schema already fully documents `projectDir` including the served-directory default and path semantics. The description adds no parameter-level detail, which meets the baseline but goes no further.

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?

States a specific verb (Evaluate) and a specific resource (`.docguard-evidence.json` against bounded local sources), which is far more concrete than a generic 'verify' claim. It does not, however, explicitly differentiate itself from the sibling `docguard_verify_claims`, so an agent must infer the split from the evidence-file mention.

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 sentence 'verification applies only to each selected statement' implies a scoping constraint, and 'bounded local sources' hints at the operating environment, but there is no explicit when-to-use guidance or named alternative such as docguard_verify_claims. Usage must be inferred.

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