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

Adds real substance beyond annotations: billing behavior, disk data retention, the non-reversible-in-practice risk that the GPU may be taken by someone else on restart, and the required scope (instances:write). This is exactly the operational context annotations like destructiveHint=false cannot convey, and nothing conflicts with them.

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 effect plus consequence in the first clause, then retention, then the restart caveat and permission. The nested parentheses in the final sentence make it slightly denser than necessary, but no sentence is 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-parameter mutation with annotations present and no output schema, the description covers cost, retention, reversibility, and authorization. The only gap is that it never hints at what comes back from the call, which is minor given the tool's simplicity.

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?

Only one parameter (instance_id) and schema coverage is 100%, so the schema already carries the meaning. The description adds no format or sourcing guidance for instance_id, leaving this at the baseline for a fully documented single-param tool.

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?

Specific verb ('Stops') plus resource ('a running server') with the immediate consequence (GPU released, billing drops to disk only). The statement that data is kept and the server can be started again implicitly separates it from destroy_instance in the sibling list, so an agent can pick correctly without opening a schema.

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 to use it (want to stop paying for GPU but keep disk contents) and the caveat that the GPU may be reassigned on restart. It doesn't explicitly name destroy_instance as the permanent-delete alternative, which is the one obvious comparison an agent would want spelled out.

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