instance_delete

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known; the description still adds real value by disclosing the asynchronous model ("Saved to the database; the scheduler applies it later") and its key limitation ("cannot confirm it is live"). It doesn't state any auth/permission requirements or what an error response looks like for a non-existent hostname, which keeps it below a 5 for a destructive mutation.

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 compact clauses, each load-bearing: what it does, how to handle multiples, and the async caveat. The primary effect and the host-keeps-running reassurance are front-loaded ahead of the routing hint.

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 destructive tool with no output schema, the description covers the essentials: effect scope, alternative for bulk, deferred application, and inability to verify liveness. The only meaningful gap is that the deferred-application warning doesn't say how to check whether the deletion actually took effect (e.g., via instance_get).

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% with a single required hostname already documented as "Instance hostname", so the schema carries the parameter burden. The description only indirectly enriches the parameter by implying the hostname must refer to a UI/API-registered instance rather than a file-declared one — a useful but thin addition over the schema.

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 one UI/API-registered instance") and immediately scopes the effect ("the host keeps running"), which separates it from instance_stop and instance_delete-adjacent siblings. The restriction to UI/API-registered instances further pins down which entities are eligible.

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?

Explicitly routes multi-delete traffic to instances_delete_bulk ("Use instances_delete_bulk for several"), giving a named alternative plus the condition that selects it. The "UI/API-registered" qualifier also implicitly excludes config-file-declared instances, so the agent knows the boundary of applicability.

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