podyx_v1_reports_evidence

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

Annotations already cover the read-only/idempotent profile, yet the description adds substantive behavior beyond them: per-resource permission rechecks, the 422/opaque-404/429 analysis_busy-with-Retry-After/500-503 error contract, and "no partial headline" on failure. The trailing line "a quote does not reserve a slot or lock a price" appears transplanted from a quoting tool and is irrelevant here, slightly muddying an otherwise strong disclosure.

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?

The auth note is correctly front-loaded and the error contract is compact, but the paragraph is a dense run of status codes and includes the off-topic quote/reservation sentence that earns no place in an evidence-read tool. Several clauses could be trimmed without loss.

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?

For a single-parameter, paginated read with no output schema, the auth, pagination and failure modes are well covered so an agent can call it correctly. The gap is that "live analysis evidence" and what it returns are never described, so the agent cannot predict the payload or judge when it is the right report 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?

Reported schema coverage is 0% at the top level, and the description compensates only partially: it stresses following pagination and that invalid or inaccessible references surface as opaque 404s, which implies the reference is an opaque capability. It adds no meaning about cursor lifecycle or page_size beyond what the nested schema properties already state, which is why this sits at the minimum-viable line rather than higher.

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 gives a specific verb and resource ("Read ... live analysis evidence") plus the underlying endpoint GET /api/v1/reports/evidence, so an agent can distinguish it from podyx_v1_reports_summary or podyx_v1_reports_metrics by name. What "evidence" concretely contains is never defined, so the read target stays somewhat abstract.

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?

It states the prerequisite scopes (reports:read, clients:read for identities) and mandates "Follow all pagination", which is real operational guidance. It never says when to prefer this tool over the many sibling report tools, nor when not to use it, so the alternatives question is left to inference.

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