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

Annotations only tell the agent destructiveHint=true; the description adds the crucial detail that the default is a soft delete where 'the key stops working but stays queryable' and that permanent truly erases it. That is real behavioral context beyond the annotations, though it omits reversibility of the soft delete and any auth/permission requirements.

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 with the action and default behavior front-loaded, then the permanent alternative, then a one-line API mapping. No filler or repetition.

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 two-parameter mutation with no output schema, the description covers what most agents need: the action, the default mode, and the destructive variant. Missing are return/confirmation behavior, whether the keyId must reference an existing key, and error semantics, but these are secondary.

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, but the description adds meaning the schema lacks: it explains the consequence of the default (key still queryable) versus setting permanent (fully erased), which is the operative distinction for choosing a value. It does not add anything for keyId beyond what the schema already says.

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 ('Revoke a key') and goes further by defining the default mode and the alternate mode (soft vs. permanent erase). It is unambiguous what the tool does, though it never names or contrasts a sibling (e.g., unkey_update_key or unkey_get_key), so routing relies on the agent inferring delete-vs-update from the verb.

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?

Usage is only implied: you revoke when you want a key to stop working. The description does give mode-selection guidance ('pass permanent to erase it'), which is genuinely useful, but there is no when-not-to-use, no prerequisites, and no pointer to alternatives such as disabling via update.

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