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

The description complements the annotations by stressing permanence, noting that build_teardown removes the deployment, and mentioning required permissions. This gives the agent a clear picture of side effects and lifecycle behavior beyond the raw destructiveHint 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?

Every sentence contributes meaningful information: purpose, contrast, defaults, return values, follow-up actions, teardown, and prerequisites. The formatting is clear and there is no fluff, despite the repeated emphasis on 'PERMANENT'.

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?

Given no output schema, the description explains the return values (public_url and poll_url) and next steps. It also mentions required permissions. It stops short of fully clarifying the interplay between file_id and version_uuid, but overall provides enough context for an agent to act.

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 descriptions cover 67% of parameters; the description adds useful default behavior for version_uuid and file_id. However, project_uuid is not explained beyond its name, and the relationship between file_id and version_uuid remains somewhat implicit.

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 a specific action ('PERMANENT deploy') and distinguishes this tool from the sibling build_deploy(target='cloud_ephemeral') by emphasizing permanence and the public URL. It also references related follow-up tools, making the purpose unambiguous.

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 explicitly contrasts with the ephemeral alternative, explains default behavior when version_uuid/file_id are omitted, and provides a clear workflow: poll with build_deploy_status, then smoke test. It also states prerequisites (admin API key and platform enablement), leaving no ambiguity about when and how to use it.

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