trigger_deep_scrub

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

With no annotations, the description carries full burden. The '[WRITE][risk=low]' prefix provides some behavioral context (write operation, low risk). However, it does not disclose whether the scheduling is asynchronous, what side effects occur (e.g., if a scrub is already in progress), or any confirmation of success.

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 extremely concise, using a simple format with clear labeling. Every sentence adds value: the main action in the first line, then parameter definitions. No extraneous text.

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 scheduling command, the description covers the essential action and parameters. However, it lacks information on the return value or confirmation, and does not mention error conditions or prerequisites. Given the simplicity, it is mostly complete but could be slightly more thorough.

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 0%, so the description must explain parameters. It does so effectively: pgid is a placement group ID with an example ('2.1a') and source context, target is an optional Ceph target name. This adds significant value over the raw schema.

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 tool schedules a deep (data-integrity) scrub on a PG. The verb 'schedule' and resource 'deep scrub on a PG' are specific, and the 'deep' qualifier distinguishes it from the sibling 'trigger_scrub' (regular scrub).

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 explains the purpose and provides context for the pgid (from pg_summary/scrub_status), guiding the agent on how to obtain the parameter. It implies use for data integrity checks but does not explicitly contrast with 'trigger_scrub' or state when not to use this tool.

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