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 discloses the calculation components and the fallback behavior for missing inputs ('Missing inputs fall back to their documented defaults'). It does not explicitly assert statelessness or no side effects, but the calculator nature and output list make the tool's behavior 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 core purpose is front-loaded and the list of outputs is compact. Minor redundancy ('calculator calculator') and the duplicate title detract slightly from an otherwise tight 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 tool with five optional parameters and no output schema, the description gives the practical essentials: what is calculated, the key default fallback rule, and the main outputs. It could still be slightly more explicit about the returned shape or the role of the 'casual' input, but it is largely 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?

Schema description coverage is 100%, so the schema already documents each parameter. The description adds high-level context (e.g., holiday pay at 8%, using 'your rate' for ACC) but does not add per-parameter meaning beyond the schema. Baseline 3 applies.

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 an explicit verb ('Run') and a named resource (Employer cost calculator), and enumerates the exact calculations it performs (KiwiSaver, ACC levy, holiday pay, true annual cost). This clearly separates it from descriptive sibling tools like calculator_describe and 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 instruction to 'Run' the calculator implies it is the execution tool rather than the describe/enquiry siblings, but the description never states when to prefer it or when to use alternatives. There is no explicit exclusion or routing guidance, so usage is only implied.

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 explaining behavior. It does disclose that the tool returns information about inputs, outputs, assumptions, and tables. However, it does not explicitly state that this is a read-only, informational tool and does not actually run a calculation, which the sibling `calculate` would do.

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 front-loads the key information: inputs, outputs, and underlying assumptions/tables. Every phrase earns its place, and there is no redundancy or 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 zero-parameter, low-complexity describe tool, the description is largely sufficient. It names the main content areas an agent should expect, though it does not mention the output format or explain how this tool relates to `calculate`. These are minor gaps 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 cannot provide parameter-level detail; the baseline is therefore 4. The description still adds value by explaining that the returned content includes units, ranges, defaults, and assumptions, which helps set expectations for the output.

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 that the tool describes the calculator's inputs, outputs, assumptions, and supporting tables. This distinguishes it from the sibling `calculate` tool, which presumably performs calculations. The title is slightly ambiguous, but the description resolves the intent.

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 usage context is implied: an agent would use this when it needs to understand the calculator's parameters, defaults, or assumptions before calculating. However, there is no explicit guidance about when to use this tool instead of `calculate` or `enquiry_describe`, and no exclusions are stated.

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 fully carries the burden of disclosing behavior. It states that nothing is bought, ordered, or paid, that no quote is guaranteed, that the service is free, and that the output includes recipient details, consent wording, and confirmation method. This is unusually transparent for a tool description.

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, front-loaded with the imperative 'Read first,' and every sentence adds meaningful information about purpose, constraints, cost, and return content. There is no redundant or filler language.

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 describe tool, the description fully covers what the agent needs to know: what submit_enquiry does, what is not true about it, and what the description output will contain. Nothing important is missing for correct invocation and interpretation.

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 baseline is 4 because there is nothing for the description to clarify about parameters. The description instead focuses on output behavior, which is appropriate for a no-input describe 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 clearly identifies this tool as the 'read first' explanation of what submit_enquiry does, naming the specific resource and context (Employee Cost Calculator NZ). It also distinguishes the tool from a purchase or guaranteed quote, which helps an agent understand the tool's role among siblings.

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 phrase 'Read first' explicitly signals when to use this tool before acting, and the description clarifies what the counterpart tool (submit_enquiry) accomplishes. However, it does not explicitly mention any sibling alternatives or state when not to use this tool, so it stops short of full alternative routing.

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 behavioral disclosure burden. It openly describes this as a metadata retrieval operation listing all field attributes and implies no side effects, though it does not explicitly state that the call is read-only or has no auth requirements.

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 concise sentences, each earning its place. The first defines the output contents, and the second gives the key relationship to submit_enquiry. No filler or repeated schema 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?

For an input-free metadata tool, the description is mostly complete: it enumerates the field attributes returned and explains how to use the output. It does not specify the exact return container, but the absence of parameters and output schema makes this a minor gap.

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 parameter semantics are not applicable. The description still adds value by explaining that returned field keys are used to key answers for submit_enquiry.

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 names the exact resource, 'Every field of the Employee Cost Calculator NZ enquiry', and lists precisely what is returned: key, label, type, required status, help text, and allowed options. It also ties the output to submit_enquiry, distinguishing it from the sibling tools.

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 signals when this tool is useful: to obtain field keys so answers can be passed to submit_enquiry. It does not explicitly contrast against enquiry_describe, but the usage context is transparent and actionable.

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 so: it discloses that Step 1 validates and returns a summary, consent line and confirmation token; that Step 2 actually submits; and that a confirmation email link must be clicked before any provider sees the details. It also reproduces the exact consent text and what consent authorizes.

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-loaded with the essential framing (what it is, what it is not), then Step 1, Step 2 and the consent definition in order. The long verbatim consent quote is repeated from the schema, which costs some redundancy, but it is legally load-bearing text and the surrounding prose stays tight.

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?

No output schema and no annotations, so the description must explain outcomes itself — it names the Step 1 return values, the Step 2 side effect, and the email-verification gate. For a nested-object, multi-step mutation tool this is complete enough to call 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 documented, setting the baseline at 3. The description adds operative meaning beyond the schema: that answers should be keyed by field key from enquiry_fields, that consent=true is mandatory at both steps, and that confirmation is the token carried over from Step 1.

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 and resource ("Submits an enquiry to Employee Cost Calculator NZ") and immediately scopes it against likely misreadings ("NOT a purchase, NOT a guaranteed quote"). The two-step framing and the note that providers only see it after email confirmation make its identity distinct from the sibling calculate/enquiry_* tools.

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 sequences usage: Step 1 is called with answers + consent=true, Step 2 "only if the person agrees" with the confirmation token. That condition is a genuine when-to-use rule. It stops short of naming alternatives (enquiry_fields, enquiry_describe) as the source of answer keys, so the agent must infer that linkage.

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