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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description usefully adds that only live, non-revoked keys are returned, ordered newest first, and that the response never contains a hash or secret, only display prefix and metadata. It does not mention rate limits or the behavior of paging past the end, so it adds real value but not a fully rich behavioral picture, making 3 appropriate.

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?

Purpose and the admin-permission requirement are front-loaded in the first line, and the second sentence packs the scoping matrix and output contract without filler. It is dense and clause-heavy but every element carries information, so only a minor readability deduction applies.

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 must cover return values, and it does: display prefix plus key metadata, never hashes or secrets. Pagination and page-size semantics are fully documented in the schema, so nothing an agent needs in order to call this tool is missing.

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%: limit, cursor, orgId, and projectId all have descriptions, including the exactly-one-of rule and the malformed-cursor 400. The description restates the "an API key ignores both parameters" rule, which is already present per-parameter in the schema, and adds nothing about limit or cursor semantics. Baseline 3 fits when the schema does the heavy lifting.

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 opens with a specific verb and resource ("List API keys") and then defines the exact scope of what is listed: the caller's own live keys, or the project's/org's keys named by projectId/orgId. Combined with the title and the sibling set (which includes revoke_api_key), an agent can distinguish this read operation from the mutation siblings without opening either 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?

The description gives concrete conditions for which parameters apply — agent connections must name exactly one of projectId/orgId, while an API key ignores both — and states the permission prerequisite (admin). It does not explicitly exclude cases or name a sibling alternative (e.g. revoke_api_key, whoami), which keeps it short of a 5.

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