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

Adds behavior the annotations cannot convey: a hard quota of 10 keys per account, the irreversible fact that the key is shown only once, and the exact semantics of test mode (prefix e59_test_, sends accepted and stored but never delivered, consumes no allowance). These are the details that determine whether an agent can safely call this.

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 and quota, then the one-time-display warning, then the mode explanation. Every clause carries information; nothing is repeated from the schema or annotations.

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-param creation tool with no output schema and annotations already covering safety, the description covers quota, one-time visibility, and mode behavior well. It does not explain the label parameter or how to subsequently retrieve/revoke the key, leaving a small gap.

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 only 50% (label undocumented, mode merely 'Default live.'), and the description compensates strongly for mode by defining what a test key is and does. It adds no semantics for label, so it stops short of full coverage.

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 long-lived API key') plus the account-level cap (max 10), which no sibling (list_api_keys, auth) shares. An agent can distinguish this create operation from list_api_keys and get_account without inspecting any schema.

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 implied by 'long-lived' and by the test-mode guidance for staging and CI, but there is no explicit when-to-use/when-not statement or routing to alternatives (e.g. when to prefer an existing key via list_api_keys instead of creating another). Adequate but leaves the choice to inference.

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