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

With no annotations, the description carries the full burden and does well: it discloses the one-time visibility of the secret, the per-account quota of 10, and the non-obvious behavior of test keys (sends accepted and stored, never delivered, no allowance consumed). It omits what happens when the quota is exceeded and whether the live key requires prior verification.

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 tight sentences with no filler; the core action and its quota are front-loaded, and the mode-specific caveat follows. Every clause carries information the agent cannot get from the schema.

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 tool with no output schema and no annotations, the description covers the critical agent-facing facts: quota, one-time display of the secret, and divergent test-mode semantics. The main residual gap is the undocumented 'label' parameter and the response shape.

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% – 'mode' has just 'Default live.' and 'label' has no description at all. The description substantially compensates for 'mode' by explaining exactly what 'test' produces and how its sends behave, but it leaves 'label' entirely unexplained in both schema and description.

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 a hard scope constraint (max 10 per account). An agent can immediately distinguish this from the read-side sibling list_api_keys and from auth-related tools.

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 gives a concrete use case for the 'test' mode (staging and CI), which is genuine usage guidance. However, it says nothing about when to create a key versus using other auth mechanisms (e.g. the 'auth' sibling), or what prerequisites/permissions are needed.

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