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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety bar is lower, but the description adds almost nothing beyond the narrow claim that it will not generate or resubmit. It never explains why a tool named 'Inspect' is flagged destructive, what state could be consumed or altered, how request_key provides idempotency, or what the 'durable' evidence survives across. The inspect framing risks an agent treating this as a harmless read despite the destructive annotation.

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 short sentences, front-loaded with the purpose and followed by the single scoping exclusion; nothing is padded or repeated. The brevity is efficient rather than verbose, though the second sentence is thin enough that the space saved buys little value.

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 need not be described, but this is a high-complexity tool: nested arguments, a request_key, a catalog-version requirement, and required native skill proofs. None of the session/bootstrap expectations, the meaning of 'permitted actions,' or the destructive consequence is addressed, leaving the definition inadequate for correct invocation in a multi-step recovery workflow.

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 six parameters, nested objects, and only 50% schema description coverage, the description supplies no parameter meaning at all. The undocumented parameters (work_id, arguments.media_id, arguments.take_id, request_key) are left entirely to the schema's type and length constraints, so the description does not compensate for the coverage gap.

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 names a specific verb ('Inspect') and a specific object ('this take's durable recovery evidence and permitted actions'), which distinguishes it from nearby siblings like native.genads_recover_take, native.genads_takes, and native.genads_select_take by framing it as evidence gathering rather than recovery or selection. It stops short of naming an alternative sibling explicitly, and 'durable recovery evidence' is jargon an agent may not resolve without other context.

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?

The only guidance is a negative exclusion: 'This does not generate or resubmit.' There is no statement of when an agent should call this versus native.genads_recover_take or native.genads_takes, no prerequisite conditions (session state, catalog version, required native skills), and no note on what to do with the 'permitted actions' the tool returns.

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