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

Annotations declare read-only and idempotent behavior, but the description adds extensive behavioral disclosure: null semantics with *_withheld flags, pagination via evidence.pagination.next_cursor, retention rules for observations, withheld data classes, registry-snapshot limitations, and unknown states. This goes well beyond the safety hints.

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 first sentence is front-loaded and useful, but the remainder is a single dense block of implementation-level caveats. It would benefit from grouping, and its length is disproportionate even for a complex tool, so it reads as over-specified rather than concise.

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 carries the full return-shape burden and does so comprehensively: status, stage, model activity, pick classification, pagination, withheld/null semantics, registry comparison, and explicit unknowns. Given the tool's complexity, almost nothing an agent needs to invoke it correctly is missing.

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 coverage is 0% and the schema only defines limit, cursor, run_id, and test_id. The description explains where run_id/test_id come from and how to use cursor (follow evidence.pagination.next_cursor), but it never describes limit's page-size role or bounds, leaving one parameter undocumented in prose.

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 opening sentence names a specific verb (Inspect), resource (Agent Picks run), and scope (one project-owned run using test_id and run_id from the run list). It implicitly distinguishes this detail endpoint from the run-list and mutation siblings, though it never names the sibling tools directly.

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 tells the agent where the identifiers come from ('from the run list'), states prerequisites ('Requires Agent Picks and visibility.read'), and rules out mutation ('Cannot change or start a run'). It does not explicitly name an alternative tool for trace or list, so routing is inferential rather than fully explicit.

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