WarpSearch

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

Goes well beyond the annotations by disclosing the full status machine and, critically, that the api_key is shown only once and that a later call returns 'claimed'. That tells the agent the call is state-consuming and non-repeatable, consistent with readOnlyHint=false and idempotentHint=false. It does not say whether a failed/denied token errors or returns a status, nor anything about auth scope or rate limits on repeated polling.

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 sentences, front-loaded with the purpose before the status enumeration, and the parenthetical glosses each status term that an agent would otherwise have to guess. The status list is long but each item carries decision-relevant behavior, so it earns its space; slightly run-on for the format.

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 does the work of describing return values by enumerating every status and the key field, which is exactly what the agent needs. Gaps are minor: behavior on an invalid/unknown token and whether repeated pending polling is rate-limited are left unstated.

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 single parameter is fully documented in the schema ('the claim_token register returned'), so the description needn't restate it. The description adds no format or provenance detail beyond what the schema already says, so baseline 3 applies for a 100%-coverage single-param tool.

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 gives a specific verb+resource ('Check on a registration') plus the payoff ('receive the API key'), which is far more useful than the title 'Claim registration' alone. It implicitly distinguishes itself from the sibling `register` (this one looks up a token returned by that call), but never names `register` as the sibling that produces the input, so an agent must infer the pairing.

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 concrete loop guidance for the main ambiguous state: on 'pending', ask the user to finish and call again. It clearly implies the tool is a polling/lookup step after `register` rather than the entry point. What it lacks is explicit routing language for when this is the wrong tool (e.g., no token yet → use `register`).

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

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

Annotations only mark it as a non-idempotent, open-world write; the description goes well beyond that with side effects (email sent, nothing created until the user approves), privacy behavior (same answer whether or not the address has an account), a rate limit (3 sign-up emails per address per hour), and secret-handling guidance for claim_token.

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?

Sentences are dense and front-loaded: purpose, constraints, flow, returns, limit, in that order. It runs a bit long and repeats the free-mailbox-provider list that already appears in the email schema, which is the only wasted text.

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 four-parameter, annotation-covered write tool with no output schema, the description covers side effects, approval flow, error behavior, return fields, and the required follow-up tool. Nothing an agent needs in order to call 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?

Schema coverage is 100%, so the baseline is 3, and the description adds real constraint semantics for email (consent, work-domain requirement, failure code) plus the user-facing role/agent/name framing already spelled out in the schema. It gains a point over baseline but partly repeats the provider list already present in the email parameter description.

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?

Opens with a specific verb+resource: asking WarpSearch for an account and API key on the user's behalf. It also names the sibling tool ('pass it to claim_registration'), so the agent can place it in the two-step registration flow 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?

Explicit prerequisites (only an email the user gave you, with consent, work domain only) and explicit exclusions (personal/free providers are refused with code personal_email; ask for a work address instead of retrying). It also describes the full approval handoff the user must complete, which tells the agent when this tool is the right step versus claim_registration.

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