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

Beyond readOnlyHint=true it adds security-relevant behavior the annotations cannot express: keys are never returned in plaintext, each key carries a masked preview and a human-readable status (active, out_of_credit, rejected), and results come back in Ankra's try-order. It also discloses the caller-identity restriction and refusal cases, which is exactly the context an agent needs before calling.

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?

Front-loaded with what is returned and followed by the safety note and the alternative, so the important parts come first. The middle clause is a dense run-on that bundles status enum, ordering, and an org-policy flag together, costing some readability.

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 full burden of describing returns, and it does so field by field, including the org-level 'run on member's keys' flag and the page link. No parameters exist to document, and the safety/authorization constraints are covered.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no filtering or scoping inputs and instead spends its words on the result shape.

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?

Specific verb and resource: lists the personal Anthropic/OpenRouter API keys on the calling person's profile, and it enumerates the returned fields (id, label, provider, masked preview, status, last used). An agent can distinguish this from the many other list_* tools without opening the 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?

Explicitly routes the write path ('To add one, call request_personal_ai_key') and states hard when-not conditions: refused for a service account, AI agent, subworker, or a dispatched/autonomous run. It does not point at the other key siblings (delete_personal_ai_key, rename_personal_ai_key, reorder_personal_ai_keys, test_personal_ai_key), which leaves those choices to inference.

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