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

Annotations only declare readOnlyHint=true, but the description discloses the return shape (status 'waiting_for_person' plus a profile link), the refusal conditions, and the security invariant that no key may be requested, accepted, or repeated. That is far more behavioral context than the annotation provides, and the closing 'Read-only' is consistent with readOnlyHint.

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 purpose and return value, then follow-up, then eligibility. Slightly redundant: the 'key never enters this conversation' point is made twice, and the trailing 'Read-only' merely restates the readOnlyHint annotation.

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 parameterless tool with no output schema, the description still explains what the caller receives (a waiting status and a link), what to do next, and who is permitted to call it. Nothing an agent needs to invoke or interpret it correctly 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?

With zero parameters the schema already carries nothing to document, so the baseline is high. The description adds a meaningful contract by stating the tool takes no key and never will, clarifying that key material flows through the profile link rather than arguments.

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 action (ask the person to add their own Anthropic/OpenRouter key), names the resource, and immediately distinguishes itself from list_personal_ai_keys and test_personal_ai_key. An agent can tell exactly what this does and what it does not do (take a key) without reading further.

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?

Gives explicit when-to-use context (the person needs their own AI key), the follow-up sequence after they confirm (list_personal_ai_keys, then test_personal_ai_key), and hard exclusions: service accounts, AI agents, subworkers, and dispatched/autonomous runs. Both inclusion and exclusion criteria are spelled out.

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