site

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

With no annotations provided, the description carries the behavioral disclosure burden. It does disclose that missing inputs fall back to documented defaults and lists the outputs produced, which is helpful. However, it does not state whether the tool is read-only, whether it persists anything, or how legal/calculation rules are applied.

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 short and front-loaded with the main action, and the default-fallback sentence is useful. However, the phrase 'calculator calculator' is redundant and the semicolon-separated output list is somewhat awkward. It is concise but not polished.

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 tool has 7 parameters, no required fields, no output schema, and no annotations, so the description needs to do more work. It lists output concepts but does not explain how parameters like owpMode, irregular, or grossEarnings interact, nor does it clarify how to choose between this and sibling tools. The schema fills some gaps, but the overall context remains incomplete.

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 parameters are already documented in the input schema. The description adds no new parameter-level meaning; it only mentions defaults, which are already present as default values in the schema. This meets the baseline but does not exceed it.

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 runs the annual holiday pay calculator and lists the output categories it computes (ordinary weekly pay, average weekly earnings, weekly rate, annual holiday pay). The verb 'Run' plus the resource is clear, though it does not explicitly distinguish itself from the sibling 'calculator_describe' and contains the redundant phrase 'calculator calculator'.

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 provided about when to use this tool versus alternatives like calculator_describe or enquiry_describe. The only behavioral note is that missing inputs fall back to defaults, which is about invocation behavior rather than selection between tools.

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. It clearly indicates that the tool returns descriptive information about inputs, outputs, assumptions, and tables, and implies no calculation or mutation occurs. It stops short of explicitly stating it performs no side effects.

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 conveys all essential information without redundancy. It is front-loaded with what the tool covers and does not waste words.

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 descriptive tool, the description gives a solid overview of content coverage, including inputs, outputs, assumptions, and tables. It does not specify the return format or whether output is text, structured, or human-readable, but this is a minor gap given the tool's simplicity.

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 already exhaustively covers parameters. The description adds useful context by promising that the tool will explain inputs with units, ranges, and defaults, which is beyond the empty 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 clearly identifies the tool as explaining the calculator's inputs, outputs, assumptions, and underlying tables. It distinguishes this from the sibling 'calculate' tool by describing an informational purpose, though it does not explicitly name the sibling it is not.

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 conveys that this tool is for learning about the calculator's behavior, which implies it should be used before or instead of performing a calculation. However, it does not explicitly state when to prefer this over 'calculate' or the enquiry-related sibling tools.

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 disclosing behavior. It states the tool 'returns who receives the details, the consent wording, and how the person confirms', indicating an informational, read-only output. It also clarifies that the subject process involves no payment or purchase. However, it never explicitly says 'this tool does not submit an enquiry or modify anything', so the side-effect profile is inferred rather than stated.

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 clear, front-loaded paragraph that begins with the imperative 'Read first', then explains the tool's purpose and contents. It avoids redundant structured-field repetition and earns its sentences by adding context about the enquiry process and return values. The only minor issue is a slightly dense middle section listing what is not guaranteed.

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, no-output-schema tool, the description is functionally complete: it specifies the tool's purpose and what it returns (recipient details, consent wording, confirmation process). It provides enough context to set expectations, though it doesn't mention error behavior or whether the output is static text. Overall, nothing essential is missing for safe selection and invocation.

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 an empty input schema, so there are no parameter semantics to explain. The description appropriately avoids discussing arguments and focuses on the tool's output. This matches 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 explicitly states that the tool 'states plainly what submit_enquiry does', making its role as a descriptive/explainer tool clear. It distinguishes itself from submit_enquiry by specifying that nothing is bought, ordered, or paid and it is free, and from calculator_describe by focusing on the Holiday Pay Calculator enquiry workflow.

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' is an explicit cue to consult this tool before taking action, implying it should be used ahead of submit_enquiry. It sets expectations about what the enquiry process entails (human providers, no guaranteed quote, free) but does not name or contrast other sibling tools like enquiry_fields, leaving some routing 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?

No annotations are provided, so the description carries the behavioral transparency burden. It discloses exactly what the tool returns and clarifies that answers should be passed to submit_enquiry, reinforcing that this tool itself does not perform submission. It could mention the exact response format, but there is no misleading or hidden 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?

Two sentences with no filler. The first sentence enumerates the returned field attributes in a compact way, and the second sentence provides the follow-up action. The most important content is front-loaded.

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 tool with no parameters, no output schema, and no annotations, the description does a good job covering what data is returned and how it should be used. It does not specify whether the result is an array or object, but for a field-listing tool this is unlikely to prevent correct invocation.

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 has zero parameters, so there is nothing to document. The description adds useful contextual semantics by explaining that returned field keys are the keys to use when calling submit_enquiry, which helps the agent connect this tool's output to a sibling's input.

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 resource (Holiday Pay Calculator NZ enquiry) and the specific payload returned: every enquiry field with its key, label, type, required flag, help text, and allowed options. It is easy to distinguish from siblings like calculate and submit_enquiry because it is about field metadata, not calculation or submission.

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 actionable guidance: pass answers to submit_enquiry keyed by field key. This implies the correct workflow of fetching fields first and then submitting. It does not explicitly compare with siblings such as calculator_describe or enquiry_describe, 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 provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It reveals that the first call validates and does not submit, that the second call is required for actual submission, that an email with a click-link is sent, and that providers only see the enquiry after the link is clicked.

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?

Although the description is long, every sentence earns its place. It front-loads the critical 'not a purchase/not a quote' distinction, then presents the two-step flow in a clear, ordered structure without redundant 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?

For a two-step submission tool with no output schema, the description is complete enough. It states what is returned at each step, what the confirmation token is for, the exact consent text required, and the downstream email/click behavior, leaving minimal ambiguity for an agent.

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 schema already documents all three parameters. The description adds valuable workflow semantics beyond the schema, particularly the step-1/step-2 relationship between answers, consent, and the confirmation token, and the requirement to reuse the same answers in step 2.

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 ('Submits an enquiry'), names the target resource ('Holiday Pay Calculator NZ'), and clearly distinguishes itself from a purchase or quote. It also differentiates this tool from calculation-focused siblings by framing it as a human-provider enquiry workflow.

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 two-step usage instructions, including when to call first, when to call second, and the consent precondition. It does not explicitly name alternative sibling tools or formal 'when not to use' conditions, but it does state that this is not a purchase and not a guaranteed quote, giving useful context for selection.

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