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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds real behavioral detail beyond them: the stop is immediate ('runs at once'), irreversible ('cannot be undone'), and preserves partial results. It does not mention permission requirements, which is a minor gap.

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 tight sentences with no filler; the core action leads and the irreversibility warning follows immediately. Every clause 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 no output schema, the description usefully notes that prior results are retained, which is the key post-call expectation for a destructive cancel. It could go slightly further on what the caller receives back or whether a completed audit can be targeted.

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 0% for two required UUID parameters, so the description carries the full burden here, yet it says nothing about project_id or audit_id. Their formats and roles must be inferred entirely from the field names.

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 and resource ('Stop ... audit') and narrows the scope to 'queued or running', so the agent knows exactly which audits this applies to. It is naturally distinguished from the sibling prepare_launch_audit/prepare_schedule tools without ambiguity.

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?

Usage is implied by the state restriction ('queued or running audit'), which tells the agent when the call is valid. However, there is no explicit when-not guidance or pointer to an alternative (e.g., how to restart or fully remove an audit), leaving some routing to inference.

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