delete_instances

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

Goes well past the destructiveHint annotation: it discloses that hosts keep running, that non-UI/API-registered entries return as 'skipped' rather than erroring, that a 404 occurs if nothing can be deleted, and that the change is only persisted for the scheduler to apply later. The warning that the tool 'cannot confirm it is live' is exactly the kind of post-call expectation an agent needs for a destructive operation.

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 with the action and the routing hint, then the behavioral caveats, all in a handful of tight clauses with no filler. It is deliberately telegraphic, which makes a few fragments ('404 if none can') slightly terse but never wasteful.

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, it covers the essentials: prerequisite discovery, sibling disambiguation, per-item partial failure, and the deferred-application caveat. Nothing an agent needs before or after invoking it 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?

Only one parameter, and the schema already documents it at 100% coverage ('Hostnames to unregister, as list_instances returns them'). The description's 'by hostname' and the list_instances reference restate that rather than adding new meaning such as case sensitivity or partial-match behavior.

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 ('Unregister instances by hostname') and explicitly separates itself from siblings that manage the same hosts. The agent can tell instantly that this removes registration records, not running processes.

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 the discovery path ('use list_instances to find them') and names the alternative ('stop_instances') with the condition that selects it — if you want the host halted, this is the wrong tool. The scope limit to UI/API-registered instances further defines when it applies.

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