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

Annotations already mark destructiveHint=true, and the description adds meaningful behavioral detail: permanent deletion, the revoke-first prerequisite, the 400 error for active keys, the org:manage scope, and the exact endpoint. There is no contradiction with 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 action, then compactly covers preconditions, scope, endpoint mapping, and guardrails. Each sentence earns its place, and bold/paragraph structure makes it scannable without redundancy.

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 action with annotations already present, this is complete: the agent knows the effect, the prerequisite, the failure mode, the required scope, and the exact HTTP path. No output schema is necessary for a simple delete operation.

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?

The schema fully documents id as a UUID API key ID, and the description adds extra meaning by explaining the id must reference a revoked key and that it appears as {id} in the DELETE path. This goes beyond the schema's bare field description.

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 states a specific verb and resource ('Delete an API key' / 'Permanently deletes an API key') and distinguishes itself from revokeApiKey by requiring the key to be revoked first. The explicit DELETE /manage-keys/{id} mapping removes any ambiguity about which operation this is.

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?

It provides clear usage context: only a revoked key can be deleted, and attempting to delete an active key returns 400. This implies the revoke-then-delete workflow, though it does not explicitly name the sibling revokeApiKey as the alternative or state when not to use the tool.

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