project_cleanup

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

With no annotations, the description carries the safety burden and does so by stating the tool can remove files and by enumerating protected categories. It would be stronger if it explicitly tied removal to dry_run=false, but the behavior of removing only completed job work files is transparent.

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 short sentences; the primary action and scope are front-loaded and the second sentence adds a valuable safety exclusion without redundancy.

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?

It is sufficient for selecting the tool but not fully complete for invoking it correctly: the dry_run=false removal path and any result/return behavior are left implicit. Given the destructive potential and absence of annotations, a sentence on dry-run semantics would make it complete.

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 compensate. 'List or remove' hints at dry_run's role and 'completed job work files' gives domain meaning to project_id, but it does not explicitly map dry_run values to list-vs-remove or describe the project_id scope.

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 names a specific verb+resource: list/remove only completed job work files. It disambiguates from the many sibling tools by narrowing the scope to cleanup of completed job work files and explicitly excluding artifacts, source assets, frozen audio, and failed jobs.

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?

It gives clear context: use when the target is completed job work files. The 'Never removes...' sentence provides a when-not boundary, though it does not name alternative sibling tools for artifact or source cleanup.

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