site

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

With no annotations, the description carries the full behavioral burden. It does disclose that missing inputs fall back to documented defaults and lists the computed outputs, but it does not explain how results are returned, what assumptions or formulas are used, or whether the tool is a pure computation with 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 sentence with no wasted words beyond the duplicated 'calculator' typo. The key outputs are front-loaded and the default behavior is mentioned, making it efficient despite minor grammatical awkwardness.

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 simple calculator with all-optional parameters that are fully documented in the schema, the description covers the outputs and default behavior. However, since there is no output schema and no annotations, the response shape and the relationship between inputs and outputs are left unstated, requiring inference.

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%, with all five parameters having names, descriptions, defaults, and ranges. The description adds only generic default-fallback context, which aligns with the schema, so it does not need to repeat individual parameter semantics.

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 says to run the annual leave loading calculator and enumerates the outputs: base weekly pay, base pay for the leave period, leave loading, and penalties. This makes the operation and resource clear, though the wording is awkward ('calculator calculator') and it does not explicitly differentiate itself from siblings like 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?

There is no guidance on when to use this tool versus alternatives such as calculator_describe or submit_enquiry. The only usage-related information is about default fallback, which is behavioral rather than selection guidance.

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 behavior. It discloses the content scope (inputs, outputs, assumptions, tables), which is useful, but it does not clarify that the tool itself is read-only, how results are returned, or 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?

A single sentence with no filler. It packs the key content categories into a compact, front-loaded 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 zero-parameter informational tool, the description covers the essential content categories an agent needs to know. It could be stronger by explicitly saying it returns a description and not a calculation, but the name and sibling context mitigate this.

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 useful parameter details to add. The description appropriately references the calculator's inputs rather than the tool's own parameters, which is coherent for a describe-style 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 the tool as providing the calculator's inputs (with units, ranges, defaults), outputs, assumptions, and tables. It is specific and informative, though it does not explicitly name or contrast the sibling calculate 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?

No explicit guidance is given for when to use this tool versus calculate or enquiry_describe. The description implies it is informational, but it does not state exclusions or alternatives.

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 behavioral disclosure burden. It transparently explains that the described action is free, involves no purchase or payment, and does not guarantee a quote. It also discloses the return contents: recipient details, consent wording, and confirmation method. It does not explicitly mention whether this tool itself is read-only, but its descriptive nature and 'returns' phrasing imply it.

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 and front-loads the most important instruction with 'Read first'. Each sentence conveys useful information without repetition, though the title is somewhat long and the phrasing occasionally reads more like user-facing copy than a tool definition.

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 simple zero-parameter descriptive tool, the description is sufficiently complete: it explains what the tool covers, what the underlying action entails, and what information will be returned. With no output schema, mentioning the return contents specifically helps an agent know what to expect.

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 are no parameter semantics for the description to explain. The baseline for a zero-parameter tool is 4, and the description correctly makes no parameter claims that could conflict with the 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 states that the tool explains what submit_enquiry does on the Leave Loading Calculator, using the verb 'states' with a named resource. It also says the tool returns who receives the details, the consent wording, and how the person confirms. However, it does not explicitly differentiate itself from sibling tools like 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 opening 'Read first' gives clear contextual guidance to consult this description before using submit_enquiry. The description also clarifies what the underlying action does and does not do, such as 'Nothing is bought, ordered or paid' and 'no quote is guaranteed'. It stops short of naming alternatives or explicitly stating when not to use this tool.

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 describes the output content but does not explicitly state that the operation is read-only or free of side effects. While the nature of the tool implies a safe read, this is not stated, leaving some ambiguity.

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, dense sentence that front-loads the key information (what fields are returned) and then provides a practical usage hint. No 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 tool with no parameters and no output schema, the description covers what it returns and how to use it. It could specify the return format (e.g., an array) but the list of attributes sufficiently informs the agent. Overall, it is adequate.

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 the baseline is 4. The description does not need to explain parameters, and it correctly focuses on the output. No additional parameter semantics are required.

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 resource (the Leave Loading Calculator enquiry fields) and lists the attributes returned (key, label, type, required, help text, options). This is clear and distinct from a general enquiry description, though it does not explicitly name a sibling tool for differentiation.

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?

It provides direct usage guidance: 'Pass answers to submit_enquiry keyed by field key.' This tells the agent how to apply the returned fields and implies calling this tool before submitting. It does not explicitly contrast with alternatives, but the 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, the description carries the full burden and discharges most of it: it discloses the two-phase flow, that step 1 only validates and returns a summary/token, that details go to up to three providers, and that an email link must be clicked before any provider sees the enquiry. It does not cover failure modes, token expiry, or what happens on duplicate submission, which is why it stops short of 5.

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 and organized as a numbered step flow, with the critical 'not a purchase' caveat up front. It is verbose, and the full consent string is reproduced verbatim even though the schema already contains it, but that repetition is arguably functional since the agent must show the consent line to the person.

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 consent-gated, two-step mutation with no output schema, the description covers the flow, the consent semantics, the privacy consequences, and the email-verification gate. An agent has everything needed to call both steps correctly and to explain the outcome to the person.

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 and the description mostly restates the schema's own documentation of answers, consent, and confirmation. It adds only the sequencing nuance that the confirmation token comes from step 1 after approval, which the schema already implies. No enum or format detail is added.

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 (enquiry to human providers) and explicitly distinguishes itself from the sibling calculate tool with 'NOT a purchase, NOT a guaranteed quote'. An agent can tell this is a consent-gated enquiry submission, not a calculation or purchase, without opening any schema.

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: call with answers and consent=true first, show the person the summary and consent line, then only call again with the confirmation token 'if the person agrees'. It even names the sibling enquiry_fields as the source of the field keys, so the sequencing and the alternative are fully specified.

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