site

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

无注释，描述承担全部行为披露责任。描述仅说明会返回下一个问题或最终裁决，但未披露是否存在副作用（例如是否提交/记录答案）、无效choice时的行为、或是否修改任何状态。对流程推进型工具来说，这些不确定性是智能体选择工具时的关键决策要素。

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?

一句话完成全部核心说明，条件在前、结果在后，结构清晰，无冗余内容。'Given X and Y, return Z'句式高效传达输入输出映射，信息密度高且易解析。

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?

作为有状态流程的步进工具，描述缺少关键上下文：'下一个问题'与'最终裁决'的返回条件未说明；无输出schema导致返回值结构完全不透明；也未说明此工具在checker流程中的位置及与兄弟工具的关系。核心操作逻辑已覆盖，但在无注释和无输出schema的条件下，信息量仍不足以让智能体无误解地使用。

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?

在schema描述覆盖率为0%的情况下，描述提供了重要补偿：明确question是'question id'（而非问题文本），choice是'chosen option'的索引。但未说明question的具体格式、choice的有效范围（schema仅限制最小值为0）或如何获取合法选项列表，且参数名question与描述中的'question id'存在轻微语义错位。

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?

描述明确说明了函数的作用：给定问题ID和选项索引，返回下一步（下一个问题或最终裁决）。动词'return'和资源'next question or final verdict'清晰，与标题'Answer a question, get the next step'一致。但未明确说明checker工具间的流程关系（如与checker_start、checker_tree的衔接），与兄弟工具的区分度有限。

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?

描述未提供任何使用时机指导，未说明何时使用此工具而非checker_start、checker_tree或enquiry_describe。没有'当...时使用'或'不要使用...'的条件说明，也没有提及前置条件（如必须先开始一个检查流程）。智能体无法仅凭此描述判断该工具在整个流程中的调用位置。

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It indicates this is the first question in a decision guide, which suggests a read-like, non-mutating start, but it does not explain whether calling it advances state, displays the question, returns options, or requires any preceding action.

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, concise sentence with no filler. It front-loads the essential fact—that this is the first question of the guide—and every word 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 starting step, the description is enough to identify when to invoke it, but without an output schema or any note about what the tool returns (the question text? a prompt? a state change?), an agent cannot fully anticipate the result. It is minimally adequate but leaves the behavior of the call unclear.

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 and the schema coverage is effectively complete, so there is nothing the description needs to add about parameter meaning. The baseline of 4 applies because no parameter semantics are required.

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 identifies a specific resource—the first question of the 'What applies when you leave?' decision guide—and clearly positions it as the entry point. It is distinguishable from the sibling checker_answer and checker_tree tools, which appear to handle subsequent steps, though it does not state what the question itself is.

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 this tool should be used to begin the decision guide, but it never explicitly says 'call this when starting the guide' or contrasts it with checker_answer, checker_tree, or the enquiry_* tools. Usage context is present only by implication, not direct guidance.

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?

With no annotations, the description must carry the behavioral burden itself. It discloses the output composition (every question, option, verdict) but does not explicitly say the tool 'returns' this data or describe any operational traits such as response size, structure, or read-only status. Still, the lack of parameters and the static description imply a safe, read-only retrieval, so it is adequate but not rich.

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 that front-loads the content ('Every question, option and verdict') and ends with the purpose. No filler; every word contributes.

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 tool with no parameters and no output schema, the description is largely self-sufficient: it tells an agent that the entire decision tree is available in one call for end-to-end reasoning. It doesn't detail the tree's format or how to combine it with sibling tools, but such details are not essential for a whole-tree resource.

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 takes zero parameters and the schema is an empty object, so there are no parameter semantics for the description to add. Baseline for 0-param tools is 4, and the description correctly avoids inventing parameter details.

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 identifies the resource—the complete decision tree of the 'What applies when you leave?' guide—and signals its scope ('Every question, option and verdict', 'whole' from the title). It lacks an explicit verb like 'returns' or 'lists', which prevents a 5, but it clearly differentiates from stepwise siblings by emphasizing end-to-end content.

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 phrase 'for reasoning end to end' explicitly states the intended use case: obtaining the full tree rather than a single answer or start step. It does not name the sibling tools or state when not to use it, so it falls short of a 5, but the context is 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?

With no annotations, the description carries the full burden. It discloses what the tool returns: an explanation of submit_enquiry, recipient details, consent wording, and confirmation method. However, it does not explicitly state that this tool itself has no side effects or how the output is structured.

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 brief and front-loaded with 'Read first,' making the intended use immediately clear. It is slightly repetitive in saying 'States plainly what submit_enquiry does' and then restating that content, but overall it is concise and well organized.

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 informational tool, the description covers what the tool explains, the key caveats about the enquiry not being a purchase or guaranteed quote, and the specific content it returns. Without an output schema, a bit more detail on the exact output format would be helpful, but this is sufficient for the tool's simplicity.

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 and the input schema is empty, so there are no parameter semantics to clarify. The baseline of 4 applies because the description adds useful context about the tool's informational purpose even though no parameter documentation is needed.

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 that the tool explains what submit_enquiry does: it starts an enquiry with human providers who quote directly, with no purchase or guarantee. It is distinct from the sibling submit_enquiry tool, though it does not explicitly contrast itself with the other sibling tools.

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 instruction 'Read first' clearly signals when to use this tool: before using submit_enquiry. It provides context for a pre-submission explanatory step, but it does not explicitly mention alternatives or when not to use it.

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?

No annotations are provided, so the description carries the full burden. It transparently enumerates what the tool exposes and clarifies that submission happens elsewhere via submit_enquiry, implying this is a non-mutating metadata operation. It could be stronger with an explicit 'read-only' statement, but the behavior is otherwise well disclosed.

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 dense sentence that front-loads the core output contents, followed by a useful cross-reference to submit_enquiry. Every phrase earns its place; there is no filler or repetition of the title.

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 must explain return values, and it does so thoroughly: key, label, type, required, help text, and allowed options. It also names the downstream consumer (submit_enquiry) and how to key answers. Nothing else is needed for an agent to correctly use this metadata tool.

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 and an empty input schema, so there are no parameter semantics to document. The baseline of 4 applies; the description correctly avoids inventing parameters and instead directs relevant field-key information toward submit_enquiry.

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 specifies the resource (the Exit Tax Estimator enquiry) and the exact content of the tool's output: field key, label, type, required flag, help text, and allowed options. It is identifiable as a field-metadata listing tool, though it lacks an explicit verb like 'returns' or 'lists' and does not directly contrast itself with the sibling enquiry_describe.

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 gives a practical usage hint: 'Pass answers to submit_enquiry keyed by field key,' which tells the agent how to consume the output. However, it does not explicitly state when to prefer this tool over related siblings such as enquiry_describe or checker_tree, so the usage guidance is implied rather than explicit.

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?

No annotations are provided, so the description carries the full burden. It discloses the two-call behavior, that validation returns a summary/consent line/token, that submission triggers an email the person must click before providers see it, and the exact consent wording. This is strong behavioral disclosure beyond the raw action.

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 dense but every sentence earns its place. The non-purchase disclaimer is front-loaded, Step 1 and Step 2 are cleanly separated, and the consent text is included because it is operationally necessary. No filler or repetition.

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 two-step workflow is fully specified: first call with answers and consent to get a summary/token, second call with token only after agreement, and the email-verification requirement. Return values are summarized despite no output schema. The description provides everything an agent needs to invoke the tool correctly.

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 real semantic value by explaining that answers must be keyed by field keys from enquiry_fields and, crucially, that confirmation is the token returned in Step 1 and must be included in Step 2. This goes beyond the schema descriptions.

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 opens with a precise verb and resource: 'Submits an enquiry to Exit Tax Estimator.' It immediately clarifies what the tool is not ('NOT a purchase, NOT a guaranteed quote') and states the two-step nature, making it clearly distinct from sibling tools like enquiry_describe and checker_start.

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 gives a clear usage flow: Step 1 validates and returns a confirmation token, Step 2 submits only after the person agrees. It also references enquiry_fields for answer keys, implying prerequisite context. It does not explicitly name alternative tools or state when not to use it beyond 'not a purchase,' so it stops short of a 5.

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