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

No annotations are provided, so the description carries the full burden. It usefully discloses the retention window (live + last ten) and that the rollback is recorded as a new deploy, which are non-obvious behaviors. However it omits permission requirements, reversibility, and what happens to the prior live deploy.

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?

A single efficient sentence pair with the key constraint (ready, retained) front-loaded and no filler.

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?

For a one-param mutation tool with no annotations and no output schema, the description covers the core behavior and eligibility but leaves gaps around auth, reversibility, and return value. Adequate but not 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 description coverage is 0% and deployId is undocumented in the schema. The description implies deployId must reference an earlier ready deploy and mentions the retention window, which adds real meaning. But it doesn't state the ID format or how to obtain a valid deployId.

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?

Clear verb 'roll back' plus specific resource 'Codebase-hosted site' to an earlier ready deploy. Distinct action from siblings like codebase_deploy or codebase_publish, though it doesn't explicitly name an alternative tool.

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 parenthetical clarifies which deploys are eligible ('ready', 'live one and last ten'), implicitly guiding selection of deployId. But there is no explicit when-to-use versus alternatives like codebase_deploy or codebase_list_deploys for finding a valid deployId.

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