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

Annotations only flag destructiveHint=true; the description goes well beyond by disclosing the exact blast radius — billing stops, non-persistent data is destroyed, persistent filesystems survive, and the action is irreversible. It also names the underlying REST endpoint, all of which materially affects how an agent should reason about invoking it.

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 sentences, front-loaded with the verb and the most important consequence (destruction), with no filler. Every sentence carries decision-relevant information.

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 destructive tool with no output schema, the description covers the operation, its consequences, data persistence caveats and reversibility. Nothing an agent needs in order to call it safely is missing.

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% for the single instance_ids parameter, so the schema already documents format, array type and minItems. The description adds only the obvious 'by id' and no batching or id-format detail, so 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 (terminate/permanently destroy) and resource (instances by id), and the parenthetical clarifies the semantics of 'terminate' versus a softer stop. It is clearly distinguishable from siblings like lambda_restart_instances or lambda_update_instance.

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 irreversibility warning implies this should be a last resort, but the description never states when to use this instead of an alternative such as restart_instances, nor any precondition (e.g., confirm the instance id first). Usage is implied rather than guided.

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