opencdr_library_evidence

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description does add real behavioral context beyond that — the warning that historical passes do not imply latest content, current evaluator, or runtime acceptance, and the Fleet-mode vs Core-mode authority difference. It says nothing about ordering, paging mechanics, or what a page contains.

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?

Short and front-loaded, with the caveat sentence placed after the actionable instructions. The phrasing 'Use views tests (content_id)' is telegraphic and grammatically loose, costing some clarity despite the low word count.

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 five parameters, 0% schema coverage and no output schema, the definition should document pagination (after/limit), ownership scoping, and roughly what a record looks like. It covers the branch logic and the freshness caveat but leaves owner_id and paging entirely to inference, and its unexplained content_id/release_id references add ambiguity.

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%, so the description carries the burden and only partially meets it: it explains the meaningful view values and the record_id branch, but owner_id, limit and after are never explained. Worse, it references content_id and release_id, which do not appear in the input schema at all, which can mislead an agent into passing unknown arguments.

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 (read) and a specific resource set (retained tests, compilations, legacy mappings) plus the freshness dimension, which is more than a restatement of the name. It does not explicitly differentiate itself from the close sibling opencdr_library_read, so an agent must still guess at the boundary.

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?

Gives concrete conditional guidance: pick the view (tests / compilations / mappings) and omit record_id for a bounded page versus supplying it to read one exact artifact. It stops short of stating when this tool is preferred over opencdr_library_read or of any exclusions.

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