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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds substantial context beyond that: the effect on anything authenticating with the key, and the exact CONFIRMATION_REQUIRED/confirmToken handshake. This is the kind of protocol detail an agent cannot infer from structured fields.

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?

Two tight sentences: consequence first, protocol second. No filler, and the most decision-relevant fact (permanent deletion) leads.

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 2-parameter destructive tool with no output schema, the description covers consequence, confirmation flow and user-facing obligation. It omits only secondary concerns such as required permission scope or what happens to keys already inactive.

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%, so the baseline is 3. The description nevertheless adds real meaning to confirmToken by explaining it must accompany an identical repeat of the original arguments, which clarifies why the parameter exists rather than just what it holds.

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 ("Delete an API key") and immediately qualifies permanence. It is cleanly separable from sibling tool names like rotate_api_key, create_api_key and list_api_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 description clearly establishes the destructive-use context and prescribes the required two-call protocol with a user confirmation step in between. It doesn't explicitly contrast with rotate_api_key for the "keep the key but change the secret" case, so no explicit alternative routing.

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