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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, but the description adds crucial context annotations cannot express: this is a dry-run preview with no side effects until confirm_change is called, and the launch is refused if it needs more than max_attempts. That is meaningful behavioral disclosure beyond structured fields.

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?

Three sentences, front-loaded with the core action, followed by parameter guidance and the confirmation gate. No wasted text; each sentence earns its place.

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?

With 7 parameters, no output schema, and safety annotations present, the description covers the preview semantics, market behavior, and confirmation flow well. It omits detail on repetitions, prompt_ids, and prompt_set_id, but those are adequately served by the 100%-covered schema.

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 coverage is 100%, so the baseline is 3. The description goes further by explaining intent behind parameters: market_ids produces one audit per market (null = default market) and max_attempts caps provider attempts with refusal on exceedance, adding meaning beyond the schema's own prose.

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?

States a specific verb+resource: 'Preview launching an audit of a prompt set (or chosen prompts) on the given engines.' It clearly positions itself as the preview step, distinct from confirm_change and cancel_audit among siblings.

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?

Gives clear operational context: pass market_ids to run one audit per market, pass max_attempts to cap attempts, and 'Nothing runs until the user agrees and you call confirm_change' explicitly routes the agent to the follow-up tool. No explicit when-not-to-use, but the workflow gate is well defined.

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