site

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

With no annotations, the description carries the transparency burden. It discloses key financial assumptions such as the £25/week umbrella margin, 15% employer NI funded from the rate, and gross pay after employer costs. However, it never explicitly states that this is a pure calculation with no persistent side effects or what the response contains.

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-loaded with the action, and its list format keeps related information together. The redundant 'calculator calculator' phrase is a minor flaw, but it does not materially hurt comprehension.

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 input schema fully documents all parameters, but there is no output schema. The description lists computed components but does not clearly state the return format or confirm that the tool returns a final take-home figure, so an agent must infer some output behavior.

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?

All seven parameters have full descriptions in the schema, so the baseline is 3. The description adds contextual framing by indicating which assumptions feed the calculation, but it does not add meaningful per-field semantics beyond what the schema already documents.

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 the imperative 'Run' with a named resource, the Locum take-home calculator, making the action and subject clear. It lists the calculator's major outputs and assumptions, but it does not explicitly distinguish this tool from the sibling calculator_describe beyond the verb and name.

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 about when to use calculate versus calculator_describe or any other sibling tool. The only usage hint is the fallback-to-defaults behavior, which addresses invocation robustness rather than tool selection.

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 present, so the description carries the burden. It adequately discloses the tool's behavior by enumerating the content it returns (inputs, outputs, assumptions, tables). For a pure documentation tool with no side effects, this is sufficient, though it does not mention any special conditions like auth or rate limits.

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 packs in the essential scope: inputs with units/ranges/defaults, outputs, assumptions, and tables. No fluff, no redundancy with the title, and all critical coverage areas are 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 0-parameter documentation tool with no output schema, the description tells an agent exactly what kind of content to expect: the calculator's inputs, outputs, assumptions, and tables. Nothing needed to select and invoke the tool correctly 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?

The input schema has zero properties, so there are no parameters to document. The baseline of 4 applies because parameter semantics are not a concern here; the description correctly focuses on the informational content 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 the tool provides: the calculator's inputs (with units, ranges, defaults), outputs, assumptions, and tables. It distinguishes itself from the sibling 'calculate' tool by framing this as a descriptive/documentation tool rather than a computation tool, though it lacks an explicit verb like 'describes'.

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 by the name 'calculator_describe' and the sibling 'calculate': an agent should use this tool to understand the calculator before or instead of computing. However, there is no explicit statement of when to use this versus alternatives, so the selection rule is left 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?

With no annotations, the description carries the full burden of behavioral disclosure. It transparently states that nothing is bought, ordered, or paid, no quote is guaranteed, it is free, and it lists what the tool returns (recipients, consent wording, confirmation method). This gives an agent a clear picture of the tool's output and the nature of the enquiry, even without an output schema.

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 two sentences that front-load the key directive ('Read first') and then concisely explain the tool's purpose and return value. It is efficient and each sentence earns its place, though the title partially duplicates the content.

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 no output schema and no parameters, the description is remarkably complete: it states the purpose, the caveats, and the exact return content (recipients, consent wording, confirmation). An agent knows exactly what to expect and when to call it. Nothing essential 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?

The tool has zero parameters, and schema description coverage is trivially 100%. Per the rubric, the baseline for 0 params is 4, and the description adds no parameter information because none is needed. No deviation is warranted.

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's function: it explains what submit_enquiry does on the Locum Tax Calculator. It uses a specific verb ('states') and resource ('submit_enquiry'), and distinguishes itself from the actual submission tool and other describe tools like calculator_describe. The purpose 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 opening 'Read first' explicitly instructs the agent to consult this tool before using submit_enquiry, providing a clear usage context. However, it does not mention alternative describe tools like enquiry_fields or calculator_describe, so the guidance is not exhaustive.

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 it does disclose the tool's behavioral output thoroughly: all field attributes are enumerated. It does not explicitly say the operation is read-only or side-effect-free, but the described purpose as a field-listing tool makes that sufficiently clear.

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 compact sentences with no filler: the first defines the complete output content, and the second adds the key usage instruction. Every sentence earns its place and the information 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 parameterless tool with no output schema, the description is complete: it fully explains what the tool returns and how to apply that output when calling submit_enquiry. Nothing needed to invoke it correctly 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?

The tool has zero parameters, so the input schema is empty and the baseline is 4. The description correctly references how the output keys should be used with submit_enquiry, which is more relevant than parameter documentation here.

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 resource (the Locum Tax Calculator enquiry fields) and enumerates exactly what is exposed: key, label, type, required status, help text, and allowed options. It lacks an explicit verb like 'get' or 'list', but the meaning is unambiguous and the reference to submit_enquiry helps position it 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 description implies usage by saying 'Pass answers to submit_enquiry keyed by field key,' which tells the agent how to use the tool's output. However, it does not explicitly state when to choose this tool over alternatives such as enquiry_describe or calculator_describe, nor does it provide any when-not-to-use 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 full burden and does so richly: it discloses that a validation call returns a summary/consent line/token, that data goes to up to three firms, that an email link must be clicked before any provider sees the enquiry, and that consent can be stopped. These are exactly the non-obvious behaviors an agent needs.

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 key distinction ('NOT a purchase') is front-loaded, and the step sequence reads cleanly. The verbatim consent text is long and partially duplicates the schema's consent description, which costs a little economy, but it is arguably necessary for the agent to present to the user.

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, nested-object tool with no output schema, the description covers input expectations, the round-trip token flow, the side effects, and the downstream email confirmation. Nothing essential for correct invocation appears 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 coverage is 100% so the baseline is 3, but the description adds genuine meaning: it explains that answers are keyed by field key from enquiry_fields, that consent means the person has agreed, and that confirmation is the token returned by step 1 and only passed on the second call. This goes beyond the schema's field-level descriptions.

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 a specific verb and resource (submits an enquiry to human providers) and immediately differentiates scope with 'NOT a purchase, NOT a guaranteed quote'. An agent can distinguish it from siblings like calculate, enquiry_fields and enquiry_describe 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?

It lays out an explicit two-step procedure with precise gating: step 1 with answers+consent, then step 2 only if the person agrees, passing the token. It also states when-not (not a purchase, not a quote) and references enquiry_fields as the source of field keys, leaving little to inference.

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