site

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

No annotations are provided, so the description must fully disclose behavior. It states what the tool returns ('the next question or the final verdict') but does not mention any side effects (e.g., whether the answer is recorded, whether this advances a persistent session), the state requirements (e.g., whether the question must come from a started session), or error behavior. For a tool that returns state-dependent results, this is a significant 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 one concise sentence that front-loads the core behavior (what to provide, what to expect). No filler or redundancy.

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 two-parameter tool without an output schema, the description covers the basic input and output flow. However, the absence of usage context (starting a flow, validity of choices, handling of final verdicts) and lack of behavioral transparency (whether this is stateless) leaves an agent with reasonable but incomplete information. Given the tool's simplicity, this is borderline adequate.

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 explain the parameters. It identifies that 'choice' is the chosen option via its 'choice' index, but it does not specify that 'question' is the question ID (it says 'question id' only in prose, not explicitly that the field is an ID), nor does it define the value range of 'choice' beyond the schema's minimum 0. The description adds some meaning but leaves ambiguity about the exact nature of the 'question' parameter.

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: given a question ID and a chosen option, it returns the next question or the final verdict. It names the specific resources ('question id', 'choice') and the resource (question-answer flow) it operates on, which is clear. However, it does not explicitly distinguish itself from sibling tools like checker_start or checker_tree beyond the general flow 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?

The description implies the context of use: during a question-answering sequence, after the user has selected an option. It does not mention when not to use it or direct to alternatives like checker_start (likely to begin) or checker_tree (likely to view the question tree). The intended use is reasonably inferable but not explicitly contrasted with siblings.

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 disclosing behavior, but it only states what the tool 'is' rather than what it does. It does not mention whether calling it has side effects, whether it creates or resets a session, or what the agent should expect in return.

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 only one sentence and contains no fluff, but it is closer to a noun phrase than a useful tool definition. It is concise without being informative, essentially restating the title with the added detail that this is the first question.

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 0-parameter starter tool this may seem simple, but the absence of any output schema, annotations, or relationship to sibling tools leaves key questions unanswered: does calling this tool display a question, start a new session, or return a state object? The agent cannot predict the tool's behavior from the description alone.

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 schema coverage is 100%, so there is nothing for the description to add. The baseline of 4 applies because 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 identifies the resource (Subject access request builder) and its position (first question), so an agent can infer it is the entry point. However, it lacks an explicit action verb such as 'starts' or 'presents', and it does not distinguish itself from sibling tools like checker_answer or checker_tree beyond the word 'first'.

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?

There is no explicit guidance on when to use this tool versus its siblings. 'The first question' weakly implies using it at the beginning of a SAR request, but no alternatives, prerequisites, or when-not-to-use conditions are 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. It discloses the content and purpose of the tool but does not explicitly describe behavior such as returning the complete tree at once, whether it is read-only, or how the data is structured. The description is adequate but lacks richer behavioral detail.

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, information-dense sentence with no wasted words. It front-loads the resource and scope, and the title reinforces the content without adding redundancy.

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 tool has no parameters and no output schema, the description is mostly sufficient on its own. However, it lacks guidance on how this tool relates to the sibling checker tools and what form the returned tree takes, which would improve completeness for an agent deciding how to use it.

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 is empty, so there is no parameter semantics burden. The description does not need to explain parameters, and the baseline for zero-parameter tools applies.

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 as the Subject access request builder guide decision tree and specifies its scope: every question, option, and verdict. This implies a reference tool that provides the full tree, which distinguishes it from the step-based checker_start and checker_answer siblings, though it does not explicitly name them.

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' suggests the tool is for holistic reasoning across the whole decision tree rather than step-by-step interaction. However, it does not explicitly state when to choose this over sibling tools like checker_start or checker_answer, leaving the routing partly to inference.

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 burden of transparency. It discloses what the enquiry process is (not a purchase, free, no guaranteed quote) and what the tool returns (recipient details, consent wording, confirmation). It does not state whether the tool has side effects or requires permissions, but for a simple read/describe tool the disclosure is largely adequate.

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 compact and front-loaded with 'Read first.' The first sentence establishes purpose, and the second details key return content. Slightly wordy, but every clause 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 tool with no output schema, the description provides enough: what the tool does and what information it returns. It does not detail the exact output format or exact wording of the consent text, but that may be intentionally left to the tool's response itself.

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 there are no semantic gaps to explain. The description adds contextual meaning about the returned content, exceeding the baseline for a no-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 clearly states that the tool explains what submit_enquiry does, with specific resource ('submit_enquiry on SAR Builder') and a concrete outcome (starting an enquiry, nothing is bought, etc.). It does not explicitly contrast itself with sibling tools, but its meta/descriptive nature is evident from the 'Read first' and 'States plainly' 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?

'Read first' gives an implicit cue to use this tool before submit_enquiry, but it does not explicitly say when not to use it or name alternatives like enquiry_fields or checker_start. The guidance is implied rather than clearly 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. It discloses the returned content well and indirectly suggests this is a read-only listing tool, but it does not explicitly state behavioral aspects such as whether this tool submits anything, whether it requires authentication, or how the fields are ordered/grouped. The workflow hint ('pass answers to submit_enquiry') implies no side effects but does not state them.

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 first sentence front-loads the key content of the response, and the second sentence adds actionable context about how to use the field keys. It is efficient and well-structured.

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 no-parameter listing tool, the description is largely complete: it enumerates the fields returned and connects them to the submit workflow. There is no output schema, so the prose serves that role reasonably well, though it does not clarify the exact return format or distinguish this tool from enquiry_describe.

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 description coverage is 100%, so there are no parameters for the description to explain. The baseline for zero-parameter tools is 4, and the description appropriately focuses on the return content instead.

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 tool's resource (every field of the SAR Builder enquiry) and enumerates the specific data it exposes: key, label, type, required, help text, and allowed options. The verb is implied rather than explicit, and the description does not explicitly differentiate it from the sibling enquiry_describe, but the content specification is clear enough.

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 practical workflow hint: pass answers to submit_enquiry keyed by field key, which implies this tool is for retrieving field definitions before submitting answers. However, it does not explicitly state when to use this tool versus alternatives like enquiry_describe, nor does it mention any exclusions or conditions.

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 provided, the description carries the full burden and does so thoroughly. It discloses the two-step confirmation flow, the non-purchase nature, the exact consent wording, the email that is sent, and the condition that providers only see the enquiry after the link is clicked. This is far beyond minimal disclosure.

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 well-structured: it opens with the key clarification, then uses numbered steps to describe the flow. Every sentence adds necessary operational information, and the consent quote is included inline rather than referenced vaguely. Nothing is redundant.

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 fully covers the tool's behavior, inputs, outputs, and sequencing. With no output schema, it still explains what the user receives (summary, consent line, token) and what happens after submission (email, link click, provider visibility). It is complete for a multi-step human-submission workflow.

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 describes all three parameters, so the baseline is 3. The description adds meaningful usage context: answers are keyed by field key from enquiry_fields, and confirmation only comes from step 1 and is used after the person approves. This clarifies the lifecycle and relationships between parameters beyond the schema definitions.

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 and resource ('Submits an enquiry to SAR Builder') and immediately clarifies what it is not ('NOT a purchase, NOT a guaranteed quote'). It clearly distinguishes this tool from the enquiry_* and checker_* siblings by focusing on the submission action.

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 an explicit two-step procedure: call first with answers and consent=true to get a summary/token, then call again only if the person agrees, with the same answers and token. It also specifies the consent requirement and the required follow-up email click, 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.