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

Beyond annotations, the description discloses that work is queued and asynchronous, that it returns quickly with a run_id, and that billing fields appear when credits are reserved. It also signals mutation/non-idempotency risk with the duplicate-runs warning and user-confirmation requirement, consistent with 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?

Five short sentences, with purpose front-loaded, then parameter modes, safety, async behavior, and billing consequence. Every sentence adds operational value; no 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?

For an async create tool with two mutually exclusive modes, the description covers confirmation, return payload (run_id), polling behavior, duplicate prevention, and billing. Combined with rich schema descriptions and output schema, nothing an agent needs before invoking is missing.

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 100%, so the schema carries the parameter meaning. The description restates url/test_id mode selection and reinforces idempotency_key's duplicate-prevention purpose, but adds little beyond what the property descriptions already say.

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 opens with 'Queue a persisted Content Intelligence run,' naming the specific action, resource, and persistence behavior. It then distinguishes the two invocation modes (new url vs saved test_id), which is enough to tell it apart from sibling tools like the visibility-run creators.

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?

It gives an explicit gate, 'Use only after explicit user confirmation,' and tells the agent to poll get_sleepwalker_content_run_status until terminal rather than creating duplicate runs. It does not explicitly enumerate exclusions or alternatives such as score_sleepwalker_content for quick scoring, so it falls just short of full when-not guidance.

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