site

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

With no annotations, the description must carry behavioral disclosure. It helpfully lists the calculated outputs and explains that omitted inputs use documented defaults, but it does not clarify side effects, error behavior, or whether the operation is read-only.

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 and compact, using a single sentence with a semicolon-separated output list. There is slight redundancy in repeating 'calculator', but no meaningful waste.

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 main calculated outputs and default behavior, which is useful given there is no output schema. However, it does not explain how inputs like purchaser or extraCosts affect the results, nor does it describe the response shape, leaving some gaps for a calculator with five optional parameters.

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 100%, so the schema already documents all five parameters with defaults and ranges. The description reinforces default fallback behavior but adds no parameter-specific semantics beyond what the schema provides, making 3 the appropriate baseline.

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 action (run the late payment calculator) and names the domain outputs: statutory interest rate, interest per day, interest to date, and fixed compensation. It is clear what the tool does, though it does not explicitly distinguish itself from sibling tools such as calculator_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 instruction to 'Run the Late payment calculator' implies the usage context, and the note about missing inputs falling back to defaults gives practical guidance. However, it does not state when to use this tool versus alternatives like calculator_describe or submit_enquiry, nor does it 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?

With no annotations, the description carries the full burden. It discloses the categories of information returned (inputs, outputs, assumptions, tables), but does not state that the tool is read-only, has no side effects, or describe the return format (e.g., structured vs. text). This is adequate but leaves gaps for a metadata 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, front-loaded sentence that efficiently lists the returned content. It is appropriately sized and wastes little space, though the phrasing 'The inputs this calculator takes' could be slightly clearer as 'Returns the inputs...'.

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 zero parameters, no output schema, and no annotations, the description should fully carry the burden. It identifies the return categories but omits the return format (structured JSON vs. text), the fact that no arguments are needed, and any safety context. It is minimally adequate but not complete for an agent to call with full confidence.

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 baseline is 4. The description does not need to explain parameters, and it correctly focuses on what the tool returns rather than what it accepts.

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 makes clear this tool describes the late payment calculator's inputs, outputs, and assumptions, which is distinct from the sibling 'calculate' that presumably performs the calculation. However, it does not explicitly name or contrast with the sibling, leaving the distinction implicit through the tool name and 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?

There is no guidance on when to use this tool versus alternatives like 'calculate' or 'enquiry_describe'. The description only lists what it returns, leaving the agent to infer that it should be called before calculating to understand the calculator.

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 behavioral burden. It discloses what happens (starts an enquiry with human providers who quote directly), what does not happen (nothing bought, ordered, paid; no quote guaranteed; free), and what is returned (who receives details, consent wording, confirmation mechanism). This is substantive behavioral disclosure for a read/describe 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?

'Read first' is front-loaded as an immediate directive, and every sentence earns its place by clarifying scope, exclusions, and return content. It is dense but not bloated; only slightly redundant with the title's 'not a purchase' phrasing, which prevents a 5.

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 describe tool with no output schema, the description is complete: it explains the tool's purpose, what it does not do, and what information it returns. No additional detail an agent needs to use it correctly 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?

The tool has 0 parameters, so the schema describes nothing and the description is not required to document params. Per the rubric, 0 params earns a baseline of 4 — there is nothing more the description could add here.

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?

States a specific verb+resource ('states plainly what submit_enquiry does') and the subject (Late Payment Interest enquiries with human providers). The title reinforces the purpose by listing what you get. It clearly differentiates from siblings like calculate and submit_enquiry — an agent knows this is the explanatory/metadata tool, not the action 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?

'Read first' is an explicit directive implying it should be consulted before invoking submit_enquiry, and the exclusion 'not a purchase, not a guaranteed quote' clarifies what it is not. However, it does not name alternative tools to route between or specify when NOT to use it beyond those negations, leaving some usage context implicit.

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 of the response (key, label, type, etc.) but does not explicitly state it is a read-only operation, mention error conditions, or describe the exact return format. While the read-only nature is obvious, the lack of explicit behavioral context warrants a moderate score.

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 with no wasted words. The primary purpose is front-loaded, and the usage hint is appended concisely. Every sentence adds value, making it 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?

Given the tool's simplicity (no parameters, no output schema), the description adequately covers what is returned and how to use it. However, it does not specify the exact data structure (e.g., array of objects) or any edge-case behavior, leaving minor gaps that an agent might need to infer. This is slightly below fully 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, and the schema confirms this. Since there are no parameters to describe, the baseline of 4 applies. The description does not need to add parameter semantics, and it does not.

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 returns 'Every field of the Late Payment Interest enquiry' and enumerates the attributes (key, label, type, required, help text, options). It is specific about the resource and content, and its relationship to submit_enquiry distinguishes it from sibling tools like 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 implicitly guides usage by saying 'Pass answers to submit_enquiry keyed by field key', indicating that this tool is a prerequisite for submitting answers. However, it does not explicitly compare with alternatives like enquiry_describe or state when not to use it, so it lacks explicit 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?

With no annotations, the description carries full burden and does so: it discloses validation behaviour, what step 1 returns (summary, consent line, confirmation token), that submission triggers an email with a link the person must click before any provider sees the data, and that up to three firms may receive details with per-firm notification and opt-out. This is far beyond what a bare mutation description would provide.

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 'Step 1:'/'Step 2:' structure is well front-loaded and every sentence carries operational meaning. The one inefficiency is the full verbatim reproduction of the consent text, which already exists in the schema's consent description.

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 nested-object, no-output-schema, no-annotation mutation with real-world consequences (contact details shared with third parties), the description covers invocation sequence, return artefacts, downstream email confirmation, and consent scope. An agent has everything needed to execute both steps 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 all three parameters are already fully documented, including the consent text. The description ties `answers` to field keys from enquiry_fields and places `confirmation` in the step-2 flow, but the consent wording is quoted verbatim from the schema, so it adds little beyond the baseline.

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?

Opens with a specific verb and resource ('Submits an enquiry to Late Payment Interest') and immediately sets scope boundaries ('NOT a purchase, NOT a guaranteed quote'). It also distinguishes the two-step nature of the call, which the sibling tools (calculate, enquiry_describe, enquiry_fields) do not cover.

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?

Explicitly prescribes when to call each time: step 1 with answers and consent=true, step 2 only after the person agrees and with the confirmation token. It also tells the agent what to do with step 1's output ('show the person the summary and the consent line') before proceeding, leaving nothing to inference.

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