site

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the output ('next question or the final verdict') but does not disclose any side effects, state changes, or whether the answer is recorded permanently. The behavior beyond the core return is opaque.

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 one concise sentence that front-loads the core action and output. It wastes no words, though it could add a brief usage note without becoming bloated.

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 description covers the basic input and output, but given there is no output schema and no annotations, an agent might not know how to format the request, interpret the returned 'next question' structure, or know whether the final verdict is a terminal state. The description is adequate for a simple step in a flow but leaves room for ambiguity in a multi-step conversation.

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 clarifies that 'question' is a question id (though the schema says string) and that 'choice' is an index. However, it does not explain the format of the question id, how to obtain it (presumably from checker_start), or the range/meaning of the choice index beyond what the schema's minimum 0 implies.

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 states a specific verb ('return') and resource ('next question or the final verdict'), and clarifies that it takes a question id and a choice index. However, it does not explicitly distinguish itself from sibling tools like checker_start or checker_tree, so the differentiation is implicit rather than stated.

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 the tool is used when the user has answered a question (has a choice index) and wants to progress, which gives some context. But it does not provide explicit guidance on when to use this versus checker_start or checker_tree, nor does it mention any exclusions or alternatives.

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. It conveys that the result is the first question but does not disclose whether calling it resets progress, whether it is purely read-only, or what happens if it is called again after starting. These are material gaps for a decision guide tool.

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?

A single sentence with no filler, and the key phrase 'first question' is front-loaded. It is appropriately short for a zero-parameter tool, though it could have added one usage sentence without becoming bloated.

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 start tool, identifying the returned resource as the first question is minimally adequate, but the lack of an explicit verb, return format, and relationship to checker_answer leaves the agent to infer next steps. No output schema exists to compensate.

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 already describes an empty object, so there is nothing for the description to add. Baseline 4 applies because parameter semantics cannot be improved further.

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 as the first question of the Waste carrier, broker and dealer checker decision guide, but it is a noun phrase rather than an explicit action such as 'starts the guide' or 'returns the first question'. It is distinguishable from checker_answer and checker_tree only by the word 'first', which is weak differentiation.

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?

No guidance is given on when to call this tool versus checker_answer, checker_tree, or the enquiry tools. The word 'first' implies it is the entry point, but the description does not state that subsequent answers should be sent to checker_answer or that it should not be used mid-guide.

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 has full responsibility for disclosing behavior, but it only describes content coverage ('Every question, option and verdict') and does not mention side effects, auth needs, output format, or whether the tree is static. It gives no safety or execution context for a read operation. This is a significant transparency gap.

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, focused sentence that wastes no words and leads with the most important content ('Every question, option and verdict'). It is well-suited to the tool's simple purpose and quick to parse.

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 description conveys the tool's scope but omits details about the returned data's structure or how an agent should consume the tree in conjunction with sibling tools like checker_answer. Without an output schema or behavioral details, an agent has only a general sense of what to expect. For a no-parameter, no-schema tool, it is minimally adequate but not 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?

The tool has zero parameters, so the schema provides no information to compensate. The description adds value by explaining that the tool exposes the entire decision tree, even though no parameters are involved. Baseline 4 is appropriate for a zero-parameter 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 identifies the resource as the 'Waste carrier, broker and dealer checker guide' and states that it contains 'Every question, option and verdict,' which clearly conveys that the tool returns the entire decision tree. It distinguishes itself from siblings like checker_answer and checker_start, which handle individual steps. However, it lacks a direct action verb such as 'returns' or 'provides.'

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' implies the tool is intended for holistic traversal through the checker guide, giving some context on when to use it. There is no explicit mention of alternatives or conditions when a sibling tool would be more appropriate. The guidance remains implicit rather than directly stated.

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 of explaining behavior. It transparently covers key outcomes: no purchase, no guaranteed quote, free, and what information is returned. It also mentions that it returns who receives details, consent wording, and confirmation method, which is valuable beyond the basic tool name.

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, using three sentences to convey essential information. It front-loads the 'Read first' instruction and packs useful details efficiently. The slight overlap with the title is minor and does not reduce clarity.

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 the simple 0-parameter nature of the tool and lack of output schema, the description gives a solid overview of what the tool returns: an explanation of submit_enquiry, its consequences, and the confirmation flow. It could be more explicit about the tool being read-only/informational, but the overall context suffices.

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 parameter semantics are not applicable. The baseline of 4 is appropriate since there is no parameter information to provide or clarify.

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 this tool describes what submit_enquiry does, using phrases like 'States plainly' and 'Read first.' It distinguishes itself from the actual submit_enquiry operation by explaining that it provides information rather than performing the enquiry. However, it does not explicitly name the tool as a 'describe' action, relying on the name and context.

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?

'Read first' provides clear placement in the workflow, signaling that this tool should be used before undertaking an enquiry. It does not explicitly name alternative tools or exclusions, but the context and emphasis on reading before acting give enough direction for an 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?

There are no annotations, so the description carries the burden of explaining behavior. It transparently lists the field attributes returned and notes that options exist only where applicable, which is useful. However, it does not explicitly state that this is a read-only lookup or describe any edge cases, output formatting, or error behavior.

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 two sentences long, front-loads the core purpose, and every sentence earns its place. It lists the exact content of the response and immediately connects the output to the related submission tool without any 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?

Given no parameters and no output schema, the description does a complete job. It explains what the tool returns, which attributes are included, that options are conditional, and how the returned field keys should be used. Nothing critical is missing for an agent 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?

The tool has zero parameters, so the parameter-semantics bar is set at baseline 4. The description adds relevant context by explaining that field keys are intended to be used with submit_enquiry, which helps an agent understand the meaning of the returned keys even though there are no input parameters to document.

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 identifies the resource (fields of the Waste Carrier Check enquiry) and enumerates the returned attributes, so an agent understands what the tool provides. It does not use an explicit verb like 'list' or 'get', and it does not contrast itself with sibling tools such as enquiry_describe, but the meaning is 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?

The description gives clear usage context: obtain field definitions and then pass answers to submit_enquiry keyed by field key. It does not explicitly state when not to use this tool or name alternatives, but the usage context is strong enough to guide selection.

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?

Even though no annotations are provided, the description fully discloses the two-step side effects, the validation step, the confirmation token behavior, the follow-up email with a required link, and the exact meaning of consent. The description goes well beyond a minimal definition and clearly informs the agent about the tool's real-world impact.

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 detailed yet tightly structured, front-loading the critical 'not a purchase' distinction and then walking through the two steps in logical order. Every sentence contributes essential information: consent text, confirmation token, and the email-link condition. There is no fluff 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?

With no output schema and no annotations, the description carries the full burden of explaining return values and side effects. It clearly states what step 1 returns (summary, consent line, confirmation token), what step 2 does, and the eventual user-facing outcome. The description leaves no critical gaps for an agent to call this tool successfully.

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 already covers parameters with 100% description coverage, and the tool description adds crucial semantic context: answers must be keyed by field key from enquiry_fields, consent must be true in both steps, and confirmation must be the token returned in step 1. This transforms the parameters from generic fields into a meaningful workflow.

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 submits an enquiry to Waste Carrier Check, immediately distinguishes it from a purchase or guaranteed quote, and explains the two-step submission process. It names the specific resource and the action, making it distinct from sibling tools like checker_answer or enquiry_fields.

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 step-by-step instructions: call first with answers and consent=true, show the user the summary and consent line, then call again only after user agreement and with the confirmation token. It also specifies the required consent wording and notes that the provider only sees the enquiry after the user clicks the email link, leaving no ambiguity about when and how 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.