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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation risk is known. The description adds the deploy-in-progress refusal behavior, which is useful, but says nothing about expected downtime, whether in-flight requests are dropped, or how the restart is confirmed.

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 sentences, front-loaded with the action and its scope, then the failure precondition. No filler and nothing buried.

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?

An output schema exists, so return values need no explanation, and the single required parameter is fully documented in the schema. The remaining gap is impact disclosure for a destructive operation—downtime and blast radius—which an agent weighing the call would want.

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?

With a single parameter at 100% schema coverage, the baseline is 3, but the description genuinely adds meaning: the same serviceId restarts a site unit on shared hosting and an entire box on managed hosting. That interpretation isn't derivable from the schema's 'the id of a service on this account'.

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 gives a specific verb plus resource ('Restart the service process') and clarifies what is actually restarted in each hosting mode: the site unit on shared, the whole box on managed. That scope nuance separates it from siblings like redeploy or rollback, though it never names an alternative explicitly.

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?

'Refused while a deploy is in progress' is a concrete precondition that tells the agent when the call will fail, which is real usage guidance. It stops short of routing the agent among siblings (e.g., restart vs redeploy vs rollback), so it isn't a full when/when-not/alternatives treatment.

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