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

Annotations only carry destructiveHint=true, so the description meaningfully adds that this is a reboot rather than a destruction and that billing continues — exactly the facts an agent needs to avoid misclassifying it as a delete. It stops short of disclosing downtime, whether in-memory/ephemeral state is lost, or auth requirements, so it is strong but not complete.

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?

One sentence plus endpoint reference, with the operation and its non-destructive nature front-loaded. Every clause earns its place and nothing is padded.

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 operation with no output schema, the description supplies the action semantics, target scope, and the key non-destruction/billing behavior. It omits what the response looks like and error conditions (e.g. restarting a non-running instance), which are the only 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?

With 100% schema description coverage on a single well-documented array parameter (minItems 1, 'Ids of the instances to restart'), the schema already does the work. The description's 'one or more ... by id' roughly restates that, adding no syntax or formatting detail beyond the structured field.

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 ('Restart one or more running instances'), plus the scoping constraint ('by id') and the exact API endpoint. The parenthetical 'a reboot — the instances are NOT destroyed and billing continues' cleanly separates this operation from the destructive sibling lambda_terminate_instances without naming it.

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?

Usage is only implied: 'running instances' conveys the precondition that the target must be in a running state, and 'one or more' conveys batching. There is no explicit when-to-use/when-not guidance and no alternative tool is named (e.g. terminate_instances or update_instance), leaving the agent to infer selection from the name alone.

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