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 burden of behavioral disclosure. It does well by stating exactly what the tool returns: inputs with units/ranges/defaults, outputs, and underlying assumptions/tables. The describe framing implies a read-only operation, though it does not explicitly state that it does not perform calculations.

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 efficient sentence with no wasted words. Each clause contributes a distinct aspect: inputs, outputs, and assumptions/tables. It is appropriately sized for the tool's simple zero-parameter nature.

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 adequately explains what content the agent can expect. It could be slightly more complete by explicitly noting that it describes the calculator rather than executing it, but the essentials 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 parameters, so the baseline is 4. The description adds useful context by clarifying that the calculator itself has documented inputs and outputs, which is the subject matter being described. No schema parameters require elaboration.

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 documentation/description action for the employer cost calculator, listing the content it covers: inputs, outputs, assumptions, and tables. It is distinguishable from the calculate sibling, though the main verb is implied by the title rather than stated in the description.

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 calculate or the enquiry tools. The agent must infer from the title and sibling names that this is for understanding the calculator's behavior rather than running a calculation or submitting an enquiry.

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 available, the description carries the full burden of behavioral disclosure. It explains validation, the intermediate summary and token, the final submission, the email with a click link, and that providers only see the enquiry after that click. It also discloses the non-purchase/non-quote nature, which is important behavioral context.

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 longer than average, but every sentence earns its place given the two-step flow and lack of annotations or output schema. Key warnings are front-loaded, and the step-by-step structure makes the required sequence easy to follow without wasted 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 two-step submission tool with no annotations and no output schema, the description is remarkably complete. It covers the preconditions, the exact consent text, the required intermediate artifact, the final side effect (email), and the condition under which a provider sees the enquiry. An agent has enough context to invoke 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?

Even with 100% schema coverage, the description adds critical meaning: answers must be keyed by field keys from enquiry_fields, consent must exactly match the quoted agreement, and confirmation is the token returned from Step 1. It also explains the conditional need for confirmation, which the schema alone does not convey.

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') against a named resource (Employee Cost Calculator NZ) and immediately clarifies what it is not ('NOT a purchase, NOT a guaranteed quote'). The two-step nature is explicit, distinguishing this from straightforward calculation or description 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 provides explicit step-by-step invocation guidance: Step 1 uses answers and consent=true, Step 2 is conditional on the person agreeing and requires the confirmation token. It clearly tells the agent when to proceed and when not to, and references enquiry_fields for the correct answer keys.

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