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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds real context beyond that: the rollback starts a deploy that runs asynchronously on its own, telling the agent to poll rather than expect an immediate result. It stops short of saying what happens to the currently live version or whether traffic is interrupted.

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, no filler, with the core action and its default front-loaded ahead of the async note.

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?

Output schema exists, so return values need no explanation, and the async deploy note covers the main operational unknown. For a destructive mutation it could still mention the effect on the live site (downtime, overwriting the current version) to be fully 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 50%: serviceId is documented, version is not. The description compensates by explaining that version is optional and omitting it selects the previous version, which is exactly the semantic the schema lacks. It does not clarify version numbering or where valid values come from (list_versions).

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?

States a specific verb+resource: put an earlier version of a service live again. It also defines the default target (the previous version) versus an explicit one, which separates it from deploy/redeploy. It does not name a sibling, so it falls just short of the top band.

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 default-to-previous-version behavior implies when this is the right call versus deploy or redeploy, but no alternative or exclusion is stated explicitly. An agent must infer that redeploy (same version) and deploy (new code) are the other options.

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