captain-legal

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses key behaviors: national rules validation, structured errors, the return of a watermarked PDF and price, and the not_covered items that must be relayed. This adds substantial value over the annotations alone.

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 focused sentences, front-loaded with the primary purpose and followed by critical output/error details. Every sentence earns its place with no redundancy or vague 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?

With no output schema, the description covers the main return values (preview, price, errors, not_covered items) well. However, it omits a prerequisite like calling get_requirements first, and does not explain the user workflow beyond the immediate generation step, so it is not fully complete.

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 description coverage is low at 25% (only 'answers' has a description), and the description does not compensate. It references 'answers' but provides no explanation of document_type, country, or language, leaving agents to infer their meaning from names and patterns.

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 uses a specific verb and resource: 'Generate a draft of the document from the user's answers.' It clearly distinguishes this from siblings like purchase_document by framing it as a preview that includes a price and watermarked PDF.

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 clearly establishes the context: generate a draft from user answers and relay validation errors or not_covered items. It does not explicitly name alternatives or exclusions, but the purpose and workflow are strongly implied, so it earns a 4 rather than a 5.

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 indicate readOnlyHint=true, so the safety profile is known. The description adds a prerequisite (status_token from purchase_document) and specifies the status aspects checked (payment and delivery). It does not disclose error behavior, token validity conditions, or return specifics, but the added context is useful beyond 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?

The description is a single sentence, concise and to the point. The key information (purpose and prerequisite) is front-loaded, with no unnecessary words or repetition of schema details.

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?

The tool is simple with two parameters and read-only annotations. The description covers purpose and prerequisite but does not explain the output or any error cases. Since no output schema exists, a description of return value would improve completeness, but the current description is adequate for a straightforward read-only status check.

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 description coverage is 0%, so the description must compensate. It explains the meaning and source of status_token (requires status_token returned by purchase_document), but order_id is only implicit as the order being checked. Partial compensation, not full coverage.

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 the status of an order, specifically payment and delivery. It distinguishes itself from sibling tools like purchase_document and generate_document by focusing on status checking. The slight mismatch between the tool name (document_status) and description (order) is resolved by the clear wording.

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 usage guidance by stating it requires the status_token returned by purchase_document. This implies a usage sequence and prerequisite, but it does not mention explicit exclusions or alternative conditions. Still, it gives clear context for when to use the tool.

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?

Beyond the readOnlyHint annotation, the description reveals key behavioral traits: questions must be used verbatim, fields are ordered, and they may be conditional on previous answers. This adds significant context for safe invocation.

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 core purpose, and each sentence provides necessary behavioral detail. No filler or redundant rephrasing.

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 no output schema, the description adequately conveys what is returned (questions with validation and legal constraints), how to use them, and structural nuances (ordering, conditionality). Enough for an agent to understand the tool's role.

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 description mentions document_type and country, reinforcing their roles, but does not explain the optional language parameter. With 0% schema description coverage, the description should compensate more fully for all 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?

The description clearly states the tool retrieves 'exact questions to ask the user' for a given document type and country, with validation rules and legal constraints. This specific verb+resource combination distinguishes it from siblings like generate_document or list_document_types.

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?

Strong guidance: the tool is positioned as the 'source of truth' for the interview, with explicit instruction to use questions verbatim and not invent fields. It doesn't explicitly name alternatives but the context and imperative tone make usage clear.

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 readOnlyHint=true, so the read-only nature is conveyed. The description adds behavioral context about return content ('accurate names, prices and legal coverage') and enforces a check-before-assume mindset, without contradicting the 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?

The description is three sentences long, front-loaded with the core action, and every sentence adds value—the first states the purpose, the second explains what to discover, and the third provides a critical usage caveat. No wasted words.

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?

No output schema exists, and the description partially compensates by mentioning returned fields (names, prices, legal coverage). However, it lacks details on pagination, error handling, parameter semantics, and empty-result behavior, leaving gaps for a tool that serves as a discovery gateway.

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 schema has 0% description coverage for six parameters. The description only hints at 'country' via 'for a given country' and does not explain limit, offset, query, category, or language, leaving the agent to infer their meaning from names alone, which is insufficient for a list tool with several filter options.

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 uses a specific verb ('List') and a clearly defined resource ('legal document types Captain.Legal can generate for a given country'). It distinguishes itself from sibling tools like generate_document or purchase_document by positioning itself as a discovery step, providing accurate names, prices, and legal coverage.

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 explicitly instructs 'Call this first' and 'Never assume a document type exists — always check here,' providing clear when-to-use guidance for the tool before creating documents. It implies the workflow relative to siblings but doesn't name alternatives explicitly, which is a minor gap.

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?

Beyond the annotations, the description discloses the return of a payment link, the email delivery of the final PDF within minutes, and that e-signature is not yet available. These are useful behavioral insights that go beyond the simple hints provided by 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?

The description is efficient, using four short sentences that front-load the main purpose and add relevant details (link return, email timing, e-signature limitation) without any redundant or vague wording.

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 simple purchase tool with two parameters and no output schema, the description covers the essential flow: purchase, payment link return, and post-payment email. It does not address error conditions or parameter edge cases, but those are not critical for a straightforward action.

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 schema has 0% description coverage, and the description does not explicitly explain draft_id or customer_email. It only hints at them through 'given draft' and 'to give to the user', leaving the agent to infer their exact roles and requirements.

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 purpose: 'Purchase the final document for a given draft.' It uses a specific verb and resource, and distinguishes itself from siblings like generate_document and get_document_status by focusing on the payment/purchase step.

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 implies usage after a draft exists, and notes that it returns a payment link to give to the user, with the PDF emailed after payment. It does not explicitly name alternatives or exclusions, but the context is clear enough given the sibling tools.

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