site

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

With no annotations, the description carries the full burden and does so well: it states there is no purchase, order, or payment, no guaranteed quote, that it is free, and what the return content covers. This fully reveals the tool's informational, non-transactional nature.

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 front-loaded with the imperative 'Read first' and every subsequent sentence adds concrete, non-redundant detail: what the tool does, what it does not do, and what it returns. It is compact for the amount of useful information provided.

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 with no output schema, this description is complete: it explains the tool's role, the caveats an agent must know, and what the returned explanation covers. There are no significant gaps for an agent to call it 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 there is no parameter semantics to document. Per baseline, a 4 is appropriate; the description need not compensate for schema gaps because none exist.

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 ('states plainly') and names the exact resource ('what submit_enquiry does on Asbestos Removal Costs'), making it clear this is an explanatory meta-tool, not the submission action itself. This also differentiates it from the sibling submit_enquiry tool.

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 opening 'Read first' gives a clear signal to use this before the submission tool, and the body explains what submit_enquiry will and won't do. It does not explicitly contrast with enquiry_fields, but the intended usage 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 and does a reasonable job: it enumerates the returned field attributes and implies a read-only introspection tool by directing answer-passing to submit_enquiry. It does not explicitly state that the tool has no side effects, but nothing in the wording suggests mutation, and the sibling reference clarifies its role.

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 single sentence front-loads the resource and then delivers a compact, enumerated list of returned attributes. The final clause about passing answers to submit_enquiry earns its place by linking the output to a sibling tool. No filler or redundant 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 zero-parameter tool with no output schema, the description adequately covers the returned data and the follow-on usage with submit_enquiry. The only omissions are an explicit read-only statement and the exact output shape, but 'Every field' implies a list of field objects. This is sufficient 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 takes zero parameters, so the empty schema provides no information. The description adds meaning beyond the schema by explaining that the field keys are intended to be used as answer keys in submit_enquiry, which connects the output to a parameterized workflow. 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 specifies exactly what the tool returns: every field of the Asbestos Removal Costs enquiry with key, label, type, required flag, help text, and allowed options. The reference to submit_enquiry clearly differentiates this from the submission sibling, and the title reinforces the purpose.

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 tells the agent that this tool is the source of field keys to use when calling submit_enquiry, providing direct workflow context. It does not explicitly state when to choose this over enquiry_describe, but the field-focused content implies the right scenario. No misleading exclusions are present.

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 and excels: it discloses that step 1 does not submit anything, that the enquiry is only visible to providers after the person clicks an emailed link, and it quotes the exact consent line. It even instructs the agent on required user interaction ('show the person the summary and the consent line'). No annotation contradiction exists.

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 carries necessary operational information, and the key disambiguation ('NOT a purchase') is front-loaded. However, it is formatted as one long run-on paragraph; splitting step 1 and step 2 into distinct sentences or bullets would improve scanability without losing content.

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 and no annotations, the description tells the agent everything needed to invoke it correctly: what step 1 returns (summary, consent line, confirmation token), the exact condition for proceeding to step 2, the consent requirement, and the post-submission email-verification behavior. Nothing essential for selecting or calling this tool is missing.

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, but the description adds genuine value: it ties answers to 'field key from enquiry_fields', explains that confirmation is the step-1 token only used after approval, and clarifies the meaning of consent=true with the exact consent text. This goes beyond the schema's 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 states a specific verb (submits), a clear resource (an enquiry to human providers), and immediately disambiguates with 'NOT a purchase, NOT a guaranteed quote.' It also captures the defining two-step nature of the operation, which clearly separates it from siblings enquiry_describe and 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 two-step protocol is spelled out explicitly: step 1 validates and returns a summary/token; step 2 is only to be invoked 'if the person agrees' and passes the confirmation token. It also names the source of answer keys (enquiry_fields) and the condition for consent, leaving no ambiguity about when each call is appropriate.

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