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

Annotations declare it is not read-only, not idempotent, and not destructive; the description adds context annotations cannot express: the preview expires after 30 minutes, the 500-row ceiling, and the hard block on committing invalid previews. It does not say whether re-validating spawns a new preview or what counts as a blocking vs. warning-level error.

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 sentences with zero filler; the row limit and artifact come first, and the commit-blocking constraint lands as the decisive second sentence.

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 an output schema present, return values need no explanation, and the description still covers limits, preview lifetime, and the commit gating rule for a non-read-only, non-idempotent mutation. Minor gaps remain around required permissions and what invalidating then re-running does to an existing preview.

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 100% and both parameters, including all nested row fields, are already documented in the schema. The description's 'up to 500 normalized creator rows' merely restates the schema's maxItems and says nothing about source_name, so it adds little beyond the structured data.

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 (validate) plus resource (creator roster import) and an explicit scope cap of 500 rows, with the produced artifact (a 30-minute preview) named. It implicitly separates itself from the commit step, though it never names roster_commit_import or roster_get_import_status as the siblings it pairs with.

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 sentence 'A preview with invalid rows cannot be committed' establishes the workflow context: this is the gate that must pass before committing an import. It stops short of explicitly naming roster_commit_import as the follow-up call or stating what to do when validation fails (fix rows and re-validate).

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