site

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

With no annotations, the description carries the burden of behavioral disclosure. It adds useful context that missing inputs fall back to documented defaults, and lists apparent output components. However, it does not state that the tool is a pure calculation with no side effects, nor describe the return format beyond the brief list.

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 concise at two sentences, but the duplicated word 'calculator' and the unlabeled semicolon list reduce structural quality. The key behavior (default fallback) is saved for the second sentence, which is fine, but the overall presentation is slightly sloppy.

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 9 parameters, no output schema, and no annotations, the description is too thin. It does not explain what the full return value is, how inputs like service, noticePay, and publicHolidays factor into the calculation, or which inputs are relevant in which employment scenarios. An agent would struggle to know what to expect from the 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add any parameter-level meaning beyond the schema; it only references concepts like 'unused annual holidays' and '8% of gross earnings' without mapping them to the named parameters.

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 verb 'Run' and names the resource 'New Zealand final pay calculator', which distinguishes it from sibling tools like calculator_describe and submit_enquiry. However, the typo 'calculator calculator' and the ambiguous semicolon-separated list (inputs vs. outputs) prevent full clarity.

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 alternatives. The phrase 'Run the New Zealand final pay calculator' implies a calculation use-case, but it does not mention calculator_describe, submit_enquiry, or any conditions or 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 provided, the description carries the full burden of behavioral disclosure. It transparently states the tool is descriptive, listing the categories of information it returns (inputs, outputs, assumptions, tables), which implies it is a read-only informational tool. It does not specify whether the output is structured text, JSON, or a document, but for a describe-type tool, this is reasonably 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 a single, compact sentence that efficiently enumerates the main content categories: inputs, outputs, assumptions, and tables. It avoids redundancy and front-loads the key information. It could be slightly more direct with a leading verb like 'Describes...', but it remains appropriately sized 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 has no parameters and no output schema, the description supplies the essential context: it returns calculator documentation including inputs, outputs, and underlying assumptions. This is sufficient for an agent to know what to expect. It does not explicitly state the format or purpose of the returned information, but the description is complete enough for 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 accepts zero parameters, so there are no parameter semantics to clarify. Per the baseline, a no-parameter tool receives a 4 because parameter documentation is irrelevant. The description appropriately focuses on the informational content returned rather than parameters.

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 what this tool provides: the calculator's inputs, outputs, assumptions, and tables. It identifies a specific resource (New Zealand final pay calculator) and distinguishes it from the sibling calculate tool by indicating this is descriptive metadata rather than the calculation itself. A minor gap is that it lacks an explicit action verb, reading as a noun phrase, but the intent is unambiguous.

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 usage: an agent would call this to understand the calculator's behavior before or instead of invoking calculate. However, it does not explicitly state when to use this tool versus its siblings, nor does it mention any exclusions or prerequisites. The usage context is inferable but not spelled out.

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 handles it well: it disclaims purchases, orders, payments, and guaranteed quotes, states it is free, and discloses what information is returned. This gives the agent confidence that invoking this tool is informational rather than side-effectful.

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, front-loaded with 'Read first', and uses plain language to pack meaningful behavioral caveats into three sentences. It loses a point because the title repeats the 'not a purchase / not guaranteed' point in the description, creating slight 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 parameterless documentation/description tool with no output schema, the description is complete: it names the action being described, explains the real-world consequences (or lack thereof), and summarizes the returned content. There is no missing critical information an agent would need to decide whether to call 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, so the schema is trivially complete and the description does not need to explain parameter meanings. The baseline for 0-parameter tools is 4, and the description appropriately focuses on the tool's purpose rather than irrelevant parameter details.

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 explicating submit_enquiry on Final Pay Calculator NZ, with a specific verb ('states plainly'), a specific resource ('what submit_enquiry does'), and a scope that distinguishes it from actually submitting. The title reinforces the contrast with a purchase or guaranteed quote, so an agent can immediately tell this is a description 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 a clear temporal usage instruction, and the description explicitly names submit_enquiry as the action it explains, implying this should be consulted before invoking that tool. It does not explicitly compare against calculator_describe or enquiry_fields, but the intended context is clear enough.

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 burden of explaining behavior. It discloses the kind of data returned (field metadata) and even notes the conditional nature of allowed options. It does not explicitly state that the operation is read-only or describe the response shape, but for a simple introspection tool the behavioral disclosure is solid.

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 well-structured sentence that front-loads the tool's purpose and then adds a practical usage pointer. No words are wasted.

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, no output schema, and no annotations, the description covers the essential information an agent needs: what the tool provides and how that output relates to the submission workflow. It could be slightly more explicit about the output format, but the description is adequate for correct 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 takes zero parameters, so the baseline is 4. The description adds relevant context by explaining how the returned field keys should be used when calling submit_enquiry, which is more than the empty schema alone provides.

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 what the tool exposes: every field of the Final Pay Calculator NZ enquiry, including key, label, type, required status, help text, and allowed options. It is distinct enough from siblings like calculate and submit_enquiry, though it does not explicitly contrast itself with enquiry_describe or use a direct verb like 'returns'.

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 clear usage context by telling the agent to pass answers to submit_enquiry keyed by field key, which implies this tool is used to discover the available fields before submission. It does not explicitly state when not to use this tool or name alternatives, but the intended workflow 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?

No annotations are provided, so the description carries the full burden and does so well: it discloses the two-call sequence, that step 1 only validates and returns a summary/token, that submission triggers a mandatory email click before any provider sees the data, that no more than three firms receive details, and that the person can stop further distribution.

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?

Front-loads the most decision-relevant fact ('NOT a purchase') and uses clear Step 1/Step 2 structure. It loses a little economy by repeating the full consent sentence already present in the schema, which is duplication rather than new information.

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?

With no output schema, the description compensates by describing what step 1 returns (summary, consent line, confirmation token) and what the person receives after step 2 (an email with a click-through link). For a nested-object, two-phase tool with no annotations, nothing essential for correct invocation 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 description coverage is 100% and the schema already documents all three parameters, including the consent text verbatim. The description adds workflow meaning for the token ('from step 1, after the person has approved the summary') and the field-key convention, but largely restates what the schema provides, so it sits at 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?

States a specific verb (submits) and resource (an enquiry to Final Pay Calculator NZ) and immediately disambiguates the intent with 'NOT a purchase, NOT a guaranteed quote.' That framing cleanly separates it from calculate/calculator_describe siblings, so an agent knows this is a routing/contact request rather than a computation.

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?

Gives an explicit two-step protocol with the exact condition for the second call ('only if the person agrees') and the gating prerequisite (confirmation token from step 1). It doesn't explicitly state when to prefer this over calculate or when to call enquiry_fields first, though the reference to 'field key from enquiry_fields' implies the dependency.

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