instance_stop

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

With annotations present, the description still adds real value: it warns that data may be lost (a risk not conveyed by destructiveHint=false), explains that stopping an already-stopped instance is a no-op, and points at status-checking afterwards. There is mild tension with idempotentHint=false and destructiveHint=false, but the warnings are additive context rather than a flat contradiction.

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?

Front-loaded with verb, resource, and endpoint, which is good, but the repeated 'compute instance / resource' phrasing bloats every sentence and the graceful-shutdown advice is verbose. The essential warning about data loss could be stated in far fewer words.

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 mutation tool with no output schema, the description covers the important unknowns: data-loss risk, no-op behavior when already stopped, and how to verify state afterwards. It omits permissions/auth requirements and whether the call returns immediately or is asynchronous, which are the remaining gaps.

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 100%, so the baseline is 3. The description usefully says the id identifies the instance to stop, which implicitly corrects the schema's copy-paste error ('to be started in rescue mode'), but it adds nothing about x-trace-id or any id format expectations.

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 and resource ('Stop compute instance / resource by its id') plus the concrete endpoint, so the agent knows exactly what operation is performed. It does not explicitly name the closely related sibling instance_shutdown, which is the tool an agent would most likely confuse this with; the graceful alternative is described generically ('via the operating system') rather than as a sibling 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?

Gives clear context for when this hard power-off is appropriate and points to a gentler alternative (logging in and shutting down via the OS). It also states the already-stopped no-op case and suggests checking status via a retrieve call. It stops short of naming the sibling tools (instance_shutdown, instance_restart) that would make the choice unambiguous.

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