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

Annotations already cover safety (readOnly and non-destructive), so the description only needs to add extra behavioral context. It does so by disclosing the empty-result phase status and the 'claim subject' semantics, without contradicting 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 short sentences carry the core behavior and the critical caveat with no filler; the main verb and resource are front-loaded.

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?

The output schema covers the return shape and annotations cover safety, so the description does not need to repeat those. However, it omits parameter guidance for limit/subject_type and does not situate this tool relative to evidence.trace or evidence_statements.search, leaving an agent to infer the rest.

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?

With 0% schema description coverage, the description must explain parameters, but it only clarifies entity_id. limit and subject_type receive no descriptive treatment beyond their property names and enum, leaving part of the call contract implicit.

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 names the exact operation ('Return Evidence[] edges') and the selection criterion (entity_id as claim subject), which distinguishes it from generic search/lookup siblings even without naming them. The 'empty result today' caveat further clarifies its current behavior.

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 'Phase 2 — empty result today' note implicitly tells an agent not to expect data and to consider alternatives, but no explicit when-to-use or alternative tool (e.g., evidence.trace, evidence_statements.search) is given.

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