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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: only prefixes are exposed and full keys are never retrievable after creation, which tells the agent not to expect secrets from this call.

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 short sentences, zero filler, and the most decision-relevant caveat (keys never shown again) is placed second but still prominent. Slightly docked because the lead sentence is a fragment rather than a clear statement of action.

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?

There is no output schema, so the description carries the return-value burden and does so reasonably by naming the visible fields. Minor gaps remain — ordering, pagination, and whether inactive keys appear are unstated — but the tool is simple enough that these are low-risk.

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?

Zero parameters, so the baseline is 4 by rule. The description instead characterizes the response shape (names, prefixes, last use, 30-day call counts), adding meaning where no schema fields exist.

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?

Identifies the resource precisely ("API keys on the account") and enumerates the fields returned (names, prefixes, last use, calls in 30 days), which makes it distinguishable from create_key/revoke_key siblings. It falls short of 5 because the first sentence is a noun-phrase fragment with no explicit verb like "list" or "retrieve".

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?

No explicit when-to-use statement and no named alternative, though for a zero-parameter enumeration tool the intent is self-evident — inspect existing credentials, then use revoke_key or create_key for changes. Guidance is implied by the sibling set rather than stated.

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