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

Annotations already declare this is a non-readonly, non-destructive, non-idempotent write. The description adds crucial context beyond that: the secret is returned only once and permissions must be user-supplied, both of which affect how an agent should call it. It stops short of describing what else the response contains.

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 short sentences with no filler, though the safety instruction leads ahead of the core purpose, which is slightly less front-loaded for an agent scanning for what the tool does. Every sentence carries actionable content.

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 three-parameter mutation with no output schema, the description covers the key risk points: one-time secret return and user-driven permission selection. It does not mention anything about the organizationId constraint beyond what the schema already states, but that is adequately covered there.

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 67% with terse field labels ('Tier', 'Key name'). The description compensates by explaining the omitted-tiers default ('Omit tiers for all') and by framing tiers as permissions that must be chosen by the user, adding real meaning the schema lacks.

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 uses a specific verb and resource ('Creates a key') and adds a distinguishing behavioral fact ('returns the secret once'). This cleanly separates it from sibling tools like list_api_keys, revoke_api_key, and rotate_api_key.

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 gives an explicit usage rule ('Ask the user which permissions the key needs; never choose for them') and a default-behavior rule ('Omit tiers for all'). It doesn't explicitly name alternative tools, but the sibling names (revoke, rotate, list) make the routing unambiguous.

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