site

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

With no annotations, the description carries the full burden, and it is unusually transparent: it states the tool returns an explanation of submit_enquiry, discloses what is not guaranteed or paid, and lists the specific information returned (recipient, consent wording, confirmation method). It also prevents confusion with a purchase by explicit negation.

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 and every sentence adds value: the 'Read first' instruction, a plain-language definition of the enquiry, and a summary of the returned information. The title repeats the non-purchase framing, reinforcing rather than wasting space.

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 parameterless explanatory tool with no output schema, the description is complete: it defines the tool's purpose, clarifies what it is not, and enumerates the content an agent can expect back. The only possible gap, a pointer to enquiry_fields, is not necessary for correctly invoking this 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, so parameter-level documentation is unnecessary; the description focuses on behavior and returned content rather than inputs. The baseline of 4 for a parameterless tool is appropriate, and no input semantics are missing.

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 as a plain-language explanation of what submit_enquiry does, with the 'Read first' instruction and title emphasizing it is not the submission action itself. It distinguishes itself from submit_enquiry by being descriptive rather than performative, but it does not explicitly differentiate itself from the enquiry_fields sibling.

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 an explicit signal to use this tool before calling submit_enquiry, and the description explains the practical meaning of what an enquiry is (no purchase, no guaranteed quote, free). It gives clear context for when to use it, though it does not state exclusions or when enquiry_fields would be the better choice.

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 it does well by specifying every piece of returned field data and the conditional nature of allowed options. It also reveals that the returned keys are the exact keys expected by submit_enquiry. However, it does not explicitly state whether the call is read-only or describe the response container.

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 short sentences with no filler; the first defines the output surface and the second connects it to the submitting workflow. The important resource name appears first.

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 no-parameter tool with no output schema, the description covers the essential return information and the intended follow-up call. It would be more complete if it stated the output container (e.g., list/object) and where enquiry_describe fits, since siblings are present.

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 input parameters, so the schema already covers everything and the baseline is 4. The description adds useful downstream context about how returned keys map to submit_enquiry, but no parameter semantics for this tool need explaining.

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 specific resource ('EPC Upgrade Cost enquiry') and the returned contents ('key, label, type, whether required, help text, allowed options'), so an agent can tell it exposes the field schema. It does not use an explicit retrieval verb and does not contrast with enquiry_describe, which prevents full sibling 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?

The second sentence gives a clear workflow: retrieve this field schema, then 'Pass answers to submit_enquiry keyed by field key.' This tells the agent when the tool is needed, but it does not mention when to prefer enquiry_describe or provide exclusions.

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 present, so the description carries the full burden, and it acquits itself well: it discloses that step 1 only validates and returns a summary/token, while step 2 is the actual submission; it states the email-with-link requirement and that providers see nothing until the link is clicked. It also defines consent verbatim, removing ambiguity about what the person must agree to. This is unusually transparent.

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 roughly 120 words but is structured as numbered steps and a quoted consent statement, so it is easy to parse. The 'not a purchase/not a guaranteed quote' disclaimer is front-loaded, and every sentence adds necessary operational or safety context. The length is justified by the two-step complexity.

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 explains the two-step lifecycle, the validation output of step 1, and the submission effect of step 2, including the email-link gate. The only gap is that the return value of step 2 (e.g., a success confirmation) is not described, and with no output schema the agent must infer it. Minor but worth noting.

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 input schema already covers the three parameters competently (100% description coverage), including the consent wording and the confirmation token's origin. The description adds the crucial temporal relationship: answers must be identical across both calls, consent must be true in both, and the confirmation token is obtained in step 1 and used only in step 2. This exceeds the baseline but doesn't drastically rewrite the schema.

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: 'Submits an enquiry to EPC Upgrade Cost', and immediately disambiguates 'NOT a purchase, NOT a guaranteed quote'. The two-step mechanism and the reference to enquiry_fields make it distinct from its siblings. An agent will not confuse it with enquiry_describe 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 an explicit two-step protocol: call first with answers and consent=true to obtain a confirmation token, then call again with the same answers, consent=true, and the token only if the person agrees. It also states what the tool is not (not a purchase, not a guaranteed quote), giving a clear when-not boundary. While it doesn't compare directly to enquiry_describe or enquiry_fields, it points to enquiry_fields for keying answers, which is sufficient for this context.

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