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

No annotations exist, so the description must carry full burden. It does an excellent job: it discloses the return structure, provides a critical conditional instruction (if claimed false, show verbatim), warns about the one-time nature of the link, notes that evidence is not durably recorded until claimed, and tells the agent not to paraphrase or withhold. This goes beyond basic expectations and clearly informs the agent of important behavioral traits and handling requirements.

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?

The description is concise yet rich in detail. It explains the purpose, usage, and critical behavioral instructions in three sentences without fluff. The response format is described, and the special handling note is clear. It balances brevity with necessary guidance.

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?

Given no annotations and no output schema, the description carries the full burden. It discloses the return structure (claimed, claim_url, what_claiming_gets_you) and critical caveats (one-time link, evidence not recorded, cannot be rediscovered). It doesn't explicitly state side effects or side-effect-free nature, but the nature of the tool (asking and getting link) implies read-only. The description is quite complete for a zero-parameter tool, though it omits details like response format or potential errors. A 4 is warranted.

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 has zero parameters pay({}), so schema coverage is 100% (vacuously). The description doesn't need to explain parameters because there are none. It adds value by explaining the response structure and the critical handling instructions for the claim_url. Since there are no parameters, this dimension is fully satisfied.

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 clearly states the tool's function: checking if a VITNA account has been claimed and providing the claim link. It uses a specific verb ('Ask whether') and resource ('VITNA account'), and the mention of 'get the link that claims it' distinguishes it from siblings like vitna_help or vitna_preflight, which likely handle general help or preflight checks. This is a clear, actionable purpose.

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 provides explicit triggers: 'when the user asks about their VITNA account, when you are told evidence is not being kept, or any time you want to hand the user something actionable.' This gives concrete when-to-use guidance. It does not explicitly mention alternatives or when not to use it, but it clearly differentiates from sibling tools by its specific purpose. A slight deduction because it does not state exclusions, but the guidance is strong.

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