cluster_delete

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

Annotations already mark destructiveHint=true, but the description meaningfully extends this by explaining the preview/apply dual mode, the blast_radius return value, and the refusal cases. It also warns against self-confirming without user consent, which is behavioral context far beyond the annotations.

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?

The description is front-loaded with the core purpose, then organizes safety behavior, refusal conditions, and return type in clear sections. Every sentence carries operational meaning; there is no filler or repetition of schema content.

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?

Given the destructive nature, the description fully equips an agent: prerequisites (cluster_info), associated sibling action (cluster_remove_host), preview behavior, return shape, and explicit refusal conditions. No output schema exists, so the stated return dict (action, blast_radius) is essential and present.

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%, so each parameter is already documented. The description reinforces confirm's preview-vs-apply semantics and the returned dict, but it does not substantially add new parameter-level meaning beyond what the schema provides; it instead adds usage and safety context.

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?

The description opens with a precise verb and resource: 'Delete an empty cluster', and immediately scopes it with '(no hosts must remain)'. It differentiates itself from related operations by naming cluster_remove_host as the evacuation step, so an agent can distinguish deletion from member removal.

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 description gives explicit when-to-use guidance: only empty clusters, check cluster_info first, use cluster_remove_host for evacuation, and never set confirm=True before showing the preview to the user. It also states refusal conditions, making the decision boundary clear.

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