pool_scrub_start

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

The description states "Non-destructive," while the annotations declare destructiveHint=true — a direct conflict on the same axis. It does add useful behavior (dry-run preview, no undo descriptor, don't re-issue, poll via scrub_status), but the flat contradiction with the structured safety hint is precisely what triggers a score of 1 and the Annotation Contradiction flag.

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?

Front-loaded with the [WRITE] tag and the one-line purpose, followed by short, high-signal sentences on preview, undo, and polling. The undo-descriptor aside is slightly meta but carries real information about the surrounding undo_list/undo_apply ecosystem, so little is wasted.

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 0% schema coverage, no output schema, and a mutating operation, the description covers purpose, preview, idempotency guidance, and progress tracking. It omits anything about the result shape, required privileges, or how long a scrub takes, but the essentials for calling it correctly are present.

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%, so the description must carry the load, and it does: pool_name is explained with an example ('tank'), dry_run's preview semantics are stated, and target is identified as a TrueNAS target name from config. No types, defaults, or value constraints beyond the schema are added, which keeps it just short of a 5.

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?

Specific verb + resource: "Start a scrub (integrity check) on a pool," with the mode tagged as [WRITE]. The parenthetical gloss clarifies what a scrub is, and the sibling scrub_status is named as the progress-polling counterpart, so an agent can distinguish the two without opening either schema.

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?

Explicit routing: "Pass dry_run=True to preview" and "Poll progress with scrub_status; do not re-issue." It states both the preview path and the alternative tool for progress, which is exactly the when-to-use/when-to-use-something-else guidance the dimension asks for.

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