cleanup preview

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

Annotations already mark this as read-only and non-destructive; the description reinforces that and adds useful behavioral details: the preview expires after 30 minutes, requires an API key, costs nothing, and returns specific audit artifacts. This goes beyond the annotations without contradicting them.

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?

Four short, information-dense sentences with the core purpose front-loaded. Every sentence contributes value: scope, outputs, relationship to cleanup_apply, expiry, and cost/auth. No filler or repetition of schema details.

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 single-parameter read-only tool with an output schema and annotations, the description is largely complete: it names the parameter scope, outputs, expiry, and usage context. It could clarify what consumers should do with the returned hashes or rollback payloads, but the output schema likely carries that detail.

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?

The schema only defines 'family' with an enum and no descriptions, so the description must compensate. It does mention 'events, expenses or trips', matching the enum values, which gives minimal meaning. However, it does not explain how the family value affects the audit output or what exactly 'family' represents beyond those categories.

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 specific verb ('read-only account audit') and a clear resource scope ('events, expenses or trips'), lists concrete outputs (source hashes, rollback payloads, review queue), and explicitly distinguishes itself from the sibling cleanup_apply. An agent can understand what this tool does and how it relates to the cleanup workflow.

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 description gives an explicit usage instruction: 'Review the exact candidate set before cleanup_apply.' This clearly positions the tool as a pre-apply review step. It does not name alternative tools or state when not to use it, but the read-only preview framing and 30-minute expiry provide enough context.

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