Clair

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds that it returns the exact same data as GET /api/signup, which is useful context, but doesn't add much beyond that. No contradiction with annotations.

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 with no wasted words. The key information (what it returns, that it's authoritative, and the instruction to read it before joining) is front-loaded and every sentence earns its place.

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 zero-parameter read-only tool with rich annotations, the description is nearly complete. It explains the return content and the recommended usage order. It could mention the response format explicitly, but the equivalence to GET /api/signup covers that. The absence of an output schema is mitigated by the description's explanation of what the response contains.

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, so the schema is trivially complete (100% coverage). The description adds meaning by explaining what the returned schema contains (required fields, privacy terms), which helps the agent understand the value of the response even though there's no output schema.

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 returns the authoritative JSON schema, required fields, and privacy terms for the waitlist transaction, and explicitly equates it to GET /api/signup. This is a specific verb+resource that distinguishes it from sibling tools like join_waitlist and update_waitlist.

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 says 'Read this before joining,' which gives clear context for when to use this tool (before joining the waitlist). It doesn't explicitly mention alternatives or when not to use it, but the sibling names make the distinction obvious and the instruction is actionable.

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 already declare idempotentHint true and readOnlyHint false, but the description adds significant behavioral detail beyond that: the mandatory consent condition ('consent: true is a recorded claim - assert it only with the person's consent'), the idempotent behavior ('repeats return already: true'), and the return of an edit_token for follow-ups. It also indicates the need for agent self-identification, which is not covered by annotations. No contradictions.

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 three sentences, each dense with information: the core action, the consent constraint, the idempotency behavior, the return value, and the self-identification requirement. No filler or repetition. The most critical fact (the join action) is front-loaded.

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?

Despite having no output schema, the description explains the return value (edit_token) and the idempotent response (already: true). It also specifies the consent requirement and the optional identification fields. For a simple join operation, all necessary information to call correctly is present, including behavioral nuances.

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. The description adds meaning to the consent parameter (a recorded claim requiring the person's consent) and explains the purpose of the three optional self-identification parameters ('Identify yourself with agent_name, agent_operator, on_behalf_of'). It does not elaborate on email beyond that, but the schema covers it.

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 action ('joins the named person to the Clair pilot waitlist') with a specific verb and resource. It also differentiates itself from siblings by noting it is a 'one typed transaction' and that repeats return 'already: true', implying this is for initial signups, distinct from get_signup_schema (schema retrieval) and update_waitlist (modification). No tautology.

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 context on when to use it: for a one-time join, and it implies that repeated submissions are handled (returns already: true). It also mentions self-identification for the agent. However, it does not explicitly name the alternative tools or state when NOT to use this tool (e.g., for updates), leaving some inference to the agent.

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?

Adds meaningful behavior beyond annotations: merge semantics (partial update, not replace), token-based authorization instead of email, and a concrete idempotency signal ('A repeat with nothing new returns already: true'). Consistent with idempotentHint and destructiveHint=false, with no contradictions.

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?

Three dense, front-loaded sentences: operation, authorization, and optionality/field semantics. Every sentence adds a distinct fact with no redundancy or filler.

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?

Covers the critical call-time facts (auth, idempotency, optional fields) and relies on schema/annotations for the rest. Could have mentioned the successful merge return value or consent field, but these are either in the schema or not essential for correct invocation.

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?

Description supplements the 67% schema coverage by listing the optional detail fields and giving glosses for context, why, and question. It doesn't define name/role/company beyond optionality, but those are self-explanatory and the schema already covers required parameters.

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 ('Merges follow-up details') and resource ('existing waitlist record'), with the title reinforcing it. Distinguishes this from sibling join_waitlist by emphasizing 'existing' and the edit token, making the purpose immediately unambiguous.

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 names the prerequisite (edit_token from join_waitlist) and states when not to rely on it ('email alone never authorizes a merge'). Also tells the agent that detail fields are optional, clarifying when this tool is appropriate to call.

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