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

The description frames the tool exclusively as inspection and reading ('Inspect', 'Read ... before taking action'), yet the annotations declare readOnlyHint=false and destructiveHint=true. An agent reading the description would reasonably conclude this is a safe read, which directly conflicts with the declared destructive profile. The description also offers no context on why a diagnostic tool would be destructive or what state it could alter, so the contradiction is left unresolved.

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 purpose is front-loaded in the first sentence and no sentence is pure filler; each one carries scope, series-link coverage, pre-action reading, or preparation contents. It loses a point for dense jargon and for the final sentence, which reads as an output-field list that adds little to the decision of whether to call it.

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?

An output schema exists, so return values needn't be spelled out, and the description is roughly adequate for a diagnostic inspection tool with six inputs. But for a tool annotated destructive and open-world, it should explain what risk the call carries and which inputs are mandatory proofs (read_skills, expected_catalog_version, request_key) — none of that is covered.

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 needs to compensate for the undocumented inputs, but it never mentions work_id, arguments.job_id, arguments.project_id, read_skills, request_key, or the nested arguments object shape. 'Exact generation job or preparation run/step ID' only loosely gestures at job_id and does not clarify the work_id vs project_id vs job_id relationship. Minimal added meaning over the schema.

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 concrete verb and resource: inspect an exact generation job or preparation run/step ID from scoped job diagnostics, plus the series-linked media-dispatch blocker case. That is enough to separate it from siblings like native.recover_film_studio_generation, native.list_film_studio_generation_jobs, and native.inspect_generation_job. It falls short of 5 because the vocabulary ('scoped job diagnostics', 'delegated media-dispatch blockers') is opaque and does not state in plain terms how it differs from native.diagnose_film_studio_run.

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?

'Read saved attempts, receipt/apply state and legal recovery operations before taking action' implies a read-before-recovery workflow, so intended use is inferable. However, no sibling is named as the alternative and there are no explicit exclusions, e.g. when to use native.diagnose_film_studio_run or native.inspect_generation_job instead. The guidance is implied rather than stated.

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