pool_scrub_start

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

With no annotations, the description covers key behaviors: it is a write operation ([WRITE]), non-destructive, and has no undo. It implies an asynchronous invocation by directing to poll scrub_status. However, it omits potential performance impacts and permission requirements.

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?

The description is concise and well-structured. The [WRITE] tag is front-loaded for quick identification. Each sentence adds value without redundancy. The use of bullet points for parameters is clear.

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?

Given the absence of an output schema, the description adequately covers the invocation and follow-up (poll scrub_status). It lacks details on the immediate return value (e.g., whether it returns a status or job ID) but is otherwise sufficient for the tool's complexity.

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 description adds meaning to both parameters beyond the bare schema (which has no descriptions). It explains pool_name with an example and target as coming from config. It could be more precise on the default behavior of target when not provided.

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 clearly states the verb 'Start' and resource 'scrub (integrity check) on a pool'. It also distinguishes the tool from its sibling 'scrub_status' which is for polling progress.

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 advises to poll scrub_status for progress and explicitly says 'do not re-issue', which is useful guidance. It does not, however, mention when not to start a scrub (e.g., if one is already running), though the implicit advice is to check first.

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