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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is largely covered. The description adds one genuinely useful fact beyond them: that submitted receipts and captured results survive the stop, scoping the destructiveness to in-flight work only. It still says nothing about what happens to partially generated media, whether stop is immediate or graceful, or what errors occur on an already-finished batch.

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?

A single front-loaded sentence with no filler, and the preservation clause is well placed after the action. It earns its place but is too thin for the tool's complexity, so it is efficient rather than exemplary.

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?

For a destructive, open-world mutation with five required parameters, nested arguments, and a catalog/request-key protocol, one sentence is not enough. An output schema exists so return values needn't be explained, but the definition omits prerequisites (skill proofs, catalog version sourcing, request-key idempotency) and disambiguation from the other stop/cancel tools.

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%, and the description contributes no parameter meaning at all — it does not clarify work_id versus arguments.batch_id, or the roles of request_key and publication_proposal_id, which have no schema descriptions. Only read_skills and expected_catalog_version are documented, and that is entirely in the schema, not the description, so the description fails to compensate for the coverage gap on a 6-parameter tool with nested objects.

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 states a verb plus resource ("Stop a GenAds media batch") and adds a preservation guarantee, so the core action is identifiable. However, it is nearly a verbatim restatement of the title and gives no explicit differentiation from the many adjacent stop tools (native.stop_work, native.cancel_work, native.genads_stop_export, native.genads_stop_pack_export), leaving the agent to infer that "media batch" is the distinguishing scope.

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 no when-to-use or when-not-to-use guidance, and no alternative is named. An agent cannot tell from this text whether stopping a media batch is the right call versus stopping the whole work, pausing it, or letting generation finish, which is a meaningful gap given how many sibling stop/cancel tools exist.

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