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

Adds useful behavior beyond the schema: a default page size of four blockers, an offset-based continuation, and a single-target mode via target_id, plus the reassurance 'No media/job changes.' However the annotations declare readOnlyHint=false and destructiveHint=true, and the description never explains what state could be destructive (e.g. consuming a blocker fingerprint or advancing review state). The 'no media/job changes' phrasing is scoped to media/jobs rather than a blanket read-only claim, so it narrows rather than strictly contradicts the 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?

Four compact sentences, front-loaded with the core action and immediately followed by the safety claim and drill-down mechanics. Dense jargon ('decision fingerprints', 'required refs') costs a little readability, but no sentence is filler.

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?

Corrected from an initial read: the tool is complex, but the gaps I identified are covered elsewhere. The fingerprint workflow, page-size default and drill-down are stated here; return shape is covered by the output schema; and prerequisite semantics for read_skills, request_key and expected_catalog_version are spelled out in the schema's own descriptions. An agent can call it correctly from the combined definition.

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 only 50% schema description coverage, the description partially compensates: it explains the limit default (four blockers), the continuation via nextOffset, and that target_id selects one clip/character. It says nothing about work_id, request_key, or the read_skills proof requirement, and its 'nextOffset' naming does not exactly match the request parameter 'offset', which could confuse an agent about whether it is echoing a response field or setting a request value.

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: reading film production-review blockers, candidates, required refs and decision fingerprints. The domain vocabulary ('blockers', 'decision fingerprints') is specialized but consistent, so an agent can recognise this as the pre-flight inspection step for a film review. It does not name its closest sibling (native.resolve_film_studio_production_review), leaving the read-vs-resolve distinction implicit.

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 a clear when-to-use trigger: call before voice/reference, voice-policy, pacing or continuity choices. It also explains the sequence ('Use the chosen blocker fingerprint, not the overview') and how to drill down with nextOffset or target_id. It stops short of naming the follow-up sibling that consumes the fingerprint, so the workflow boundary is only implied.

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