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

Annotations already mark the tool as destructive, but the description adds that the deletion is irreversible and may revoke the key powering the current MCP session. This is meaningful behavioral context beyond the structured 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 extremely concise, front-loads the action and resource, and includes only impactful warnings. Every element earns its place with no filler.

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 operation with annotations already covering mutability, the description provides the essential context: irreversibility and risk to the active session. Not describing response behavior is a minor gap given the absence of an output schema and low complexity.

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 input schema fully documents the id parameter as a UUID with 100% coverage, so the description does not need to compensate. The description adds minimal parameter-specific meaning, matching the baseline for well-covered parameters.

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 the precise action as DELETE /v1/agent/keys/{id} and identifies the resource as an agent key. The 'irreversible' qualifier and the explicit warning make it distinct from sibling tools like create_key and list_keys.

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 warning not to revoke the key used by the MCP session gives important context, but the description does not explicitly state when to use this tool versus alternatives or provide broader exclusion conditions. Usage is implied rather than fully specified.

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