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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the substance those hints lack: exactly what is destroyed (workspace, slug, project slot) and the failure mode for persistent projects. It stops short of stating irreversibility or recovery options, so it is strong rather than exhaustive.

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?

Three short sentences: action and effects first, the exclusion rule last. Every clause carries information an agent needs; nothing is redundant with the title or annotations.

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 single param is fully documented in the schema. The description covers the destructive scope and the sibling routing, leaving nothing an agent needs missing for correct invocation.

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?

There is a single parameter with 100% schema coverage, and the schema already explains that project_id comes from create_project or list_projects. The description adds no format, validation, or sourcing detail beyond that, so the baseline 3 applies.

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 (clean up) plus a specific resource (ephemeral project), with concrete effects enumerated: deletes the workspace, retires the slug, frees the project slot. It also names the sibling it is not (delete_project), so an agent can distinguish it 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?

States the selection condition explicitly: use this once the task is done and the project is ephemeral; persistent projects error here and should go to delete_project. Both when-to-use and when-not-to-use are covered with the named alternative.

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