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

With destructiveHint=true and idempotentHint=true already declared, the description adds meaningful context beyond the annotations: it preserves accepted provider receipts and never replays the completed phase, which tells the agent the mutation is bounded and safe to retry. It stops short of saying what a failed recovery leaves behind or what authorization/ownership checks apply.

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 tight sentences with the precondition front-loaded and no filler. The phrase "requires a diagnostic fingerprint" is the one element that costs more confusion than it returns, but overall the structure is efficient.

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?

This is a destructive, six-parameter tool with nested objects and required catalog/skill proofs, so the burden is high. The description covers the trigger and the replay-safety guarantee, and an output schema covers returns, but the unmatched "diagnostic fingerprint" requirement and the unexplained work_id/arguments/read_skills contract leave gaps an agent must guess at before calling.

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 only 50%, so the description needed to carry weight, and it does not. Worse, the only parameter-like phrase, "diagnostic fingerprint," has no corresponding field in the schema, so the agent cannot map it to work_id, request_key, expected_version, or arguments; the nested arguments object and work_id are never explained at all.

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 ("continue an owned native run") plus the exact precondition ("from a durably applied phase after its worker is stale"), which is far more informative than the title alone. It does not, however, explicitly distinguish itself from close siblings such as native.diagnose_film_studio_run, native.resume_film_work, or native.recover_film_studio_generation, so an agent still has to infer which recovery path applies.

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 a clear trigger condition (stale worker after a durably applied phase), which is real when-to-use guidance. But no alternatives are named — notably the diagnostic tool that presumably produces the required fingerprint — and the "diagnostic fingerprint" requirement is never tied to a concrete input, leaving the agent unsure how to satisfy it.

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