get_change_evidence

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, but the description adds genuinely new trust context: PR metadata comes from the importer and is not authenticated by this server. That is a meaningful caveat about data provenance that the annotations do not convey.

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 tightly written sentences with the core retrieval semantics front-loaded and the provenance caveat second. Nothing is redundant or padded.

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, five parameters at 0% description coverage, and a required 'project' parameter never referenced, the description is not complete enough to invoke this confidently. The nature of the returned 'stored runs' and the effect of limit/offset are left entirely to inference.

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 description coverage is 0% across five parameters, so the description carries the full burden. It clarifies that 'pr' is a PR number and that 'revision' is an exact revision, but never mentions the required 'project' parameter or explains 'limit'/'offset' pagination, leaving three of five parameters undocumented.

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 and resource: 'Find stored runs associated with a PR number'. Combined with the optional revision qualifier, an agent knows this retrieves persisted run records keyed by PR. It does not, however, distinguish itself from the sibling get_flow_evidence, which by name sounds adjacent.

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?

There is no when-to-use / when-not-to-use guidance and no named alternative, despite the presence of get_flow_evidence in the sibling set. The only usage signal is that a revision is optional, which is closer to parameter description than routing guidance.

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