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

Annotations already declare a non-read-only, non-idempotent, non-destructive mutation, and the description adds genuinely new behavioral facts: the raw key is returned exactly once, must be delivered and not stored, all keys carry full API access, and expiry defaults to 90 days with a 365-day ceiling. These are the details an agent needs to avoid silently losing the secret or mis-assuming scoped permissions.

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, front-loaded with the action, then the irreversible one-time-secret warning, then expiry facts. No filler and nothing that could be dropped without losing information.

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?

With no output schema, the description carries the return-value burden and does so: the created key is returned once and never again. Combined with the expiry rules and full-access statement, an agent has everything needed to call this correctly and handle the result safely.

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 a semantic constraint the schema doesn't state: every key has full API access, which reframes ip_allowlist as a network restriction rather than a permission scope. The expiry default and max in the description duplicate the schema, but the full-access note is real added value.

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 ('Create a new API key') so the agent can distinguish it from list_api_keys, revoke_api_key, and other siblings. It doesn't name those siblings explicitly, so differentiation relies on the trivially obvious verb, not on stated routing.

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 conveys usage context ('hand it to the user and never repeat or store it'), which implies this is the provisioning step in a key lifecycle. However, it never says when to use this versus list_api_keys or revoke_api_key, and gives no prerequisites about who may create keys.

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