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

Beyond the annotations (which already flag non-read-only, idempotent, non-destructive), the description adds two non-obvious behavioral facts: GPU billing resumes and instances:write permission is required, plus a user-confirmation requirement. That is real added value; it stops short of describing failure modes or the response shape.

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?

Three short clauses, front-loaded with the action and its state constraint, followed by the consequence and the permission requirement. Every clause earns its place with 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 single-parameter mutation with no output schema, the description covers what it does, the cost consequence, the authorization requirement, and the confirmation step. Only edge behavior (e.g., calling it on an already-running instance) is left to the idempotentHint annotation.

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 100% and there is a single required instance_id, so the schema carries the parameter burden. The description adds no format or sourcing guidance for the id, so the baseline 3 applies.

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 ('Starts a stopped server again') and narrows scope to stopped instances, which separates it cleanly from create_instance, stop_instance, and destroy_instance. An agent can pick it out of the sibling list without opening any 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?

The phrase 'Starts a stopped server again' gives the precondition for use, and 'Confirm with the user' and 'Needs instances:write' give operational context. It does not explicitly name an alternative tool or state when-not to use it, but the applicable state (stopped) is unambiguous.

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