site

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

With no annotations, the description carries the behavioral disclosure burden. It meaningfully reveals assumptions: umbrella margin is £25/week, Employer NI is 15% funded from the rate, and gross pay is after employer costs. It also states that missing inputs use documented defaults. It doesn't describe the output format, but for a pure calculator this is acceptable transparency.

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 only one sentence, so it is concise, but it contains the awkward repetition 'calculator calculator' and a semicolon-separated list that is not explicitly labeled as inputs, outputs, or assumptions. It is front-loaded with the main action, but the structure is slightly muddled.

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 tool has five optional parameters, no output schema, and no annotations, so the description should clarify what the result is. It lists several calculation components, which partially answers this, but it never explicitly states that the tool returns an estimated take-home amount or how IR35 status affects the calculation. This is a meaningful 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?

Schema description coverage is 100%, so the schema already documents each parameter and its default. The description adds a general fallback-to-defaults note and calculation assumptions, but it does not enrich individual parameter meanings beyond what the schema provides. Baseline 3 is appropriate.

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 verb 'Run' and clearly identifies the resource as the 'Day rate take-home calculator', so an agent can tell this is a calculation tool. The list of components (Annual invoice value, Umbrella margin, Gross pay, Employer NI) hints at what the tool computes, though it does not explicitly state 'take-home pay'. The redundant 'calculator calculator' phrasing slightly weakens an otherwise clear purpose.

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 about when to use this tool versus alternatives like calculator_describe or submit_enquiry. The only usage-related note is that missing inputs fall back to defaults, which is about behavior 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 exist, so the description must carry behavioral/safety information. It discloses the content returned (inputs, outputs, assumptions, tables), which implies a read-only informational call. It does not explicitly state side-effect-free behavior or the output format, but for a describe tool this is adequate.

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?

One tight sentence that front-loads all key content areas. No filler or repetition of the schema.

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 zero parameters and no output schema, the description names the return dimensions (inputs, outputs, assumptions, tables) sufficiently for an agent to judge relevance. It could explicitly note that no calculation is performed and that the result is informational, but sibling naming makes this inferable.

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 carries no semantics; baseline is 4. The description compensates by specifying that the tool will describe parameter units, ranges, and defaults for the calculator, adding conceptual meaning beyond the empty 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 identifies a documentation/describe purpose: it will relay the calculator's inputs (with units, ranges, and defaults), outputs, and underlying assumptions and tables. The title reinforces this. It does not explicitly contrast with sibling `calculate`, but the describe-vs-calculate distinction is evident.

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 the tool is the reference for understanding the calculator, so an agent would call it before or instead of `calculate` when needing semantics. However, it never states when to prefer this over siblings or gives exclusions, leaving the decision 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 to carry the safety profile, the description fully discloses the tool's behavior: nothing is bought, ordered, or paid; no quote is guaranteed; it is free; and it returns who receives the details, the consent wording, and how the person confirms. This goes well beyond what the empty schema or title alone could convey.

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?

Three short sentences are front-loaded with the most important instruction ('Read first') and then state the core behavior, the non-purchase guarantee, and the returned information. Every clause earns its place without jargon or padding.

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 is self-sufficient: it clarifies what this tool is for, what it is not (a purchase/quote), and what information it returns. An agent can decide to call it before submit_enquiry without any missing context.

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 and 100% coverage by definition, so there is nothing for the description to clarify. The baseline of 4 for parameterless tools applies, and the description appropriately focuses on behavior and return content instead of inputs.

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 ('states plainly'), the subject ('what submit_enquiry does on Contractor Pay Calculator'), and the scope (an enquiry with human providers who quote directly). It clearly separates this descriptive tool from the actual submit_enquiry sibling by framing itself as a read-first explanation rather than the action.

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 an explicit placement cue telling the agent to consult this tool before using submit_enquiry, and the description makes it obvious this is the explanatory counterpart to that action. It doesn't explicitly rule out alternatives such as enquiry_fields or calculator_describe, but the context is clear enough for a zero-parameter description 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, the description carries the burden of behavioral disclosure. It explains what content is returned but does not state the return format (array vs object), whether authentication is required, or that the operation is read-only. Given the tool's simple informational nature, these gaps are acceptable but leave some uncertainty.

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, front-loaded with the core content and followed by a practical usage pointer. Every sentence earns its place; no filler or repetition.

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 no-parameter metadata tool, the description is nearly complete: it lists the field attributes, mentions allowed options, and connects to submit_enquiry. The absence of an output schema is partially mitigated by listing the returned attributes, though it stops short of describing whether results are a list or keyed object.

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, and the schema coverage is 100% (vacuously), so the baseline is 4. The description adds no parameter details because there are none, but it usefully explains that output field keys are meant to be used as keys in submit_enquiry, which clarifies the relationship without describing parameters of this 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 resource (fields of the Contractor Pay Calculator enquiry) and the data exposed (key, label, type, required, help text, allowed options). It lacks an explicit verb like 'lists' or 'returns', but the colon structure and content make the purpose clear. It is distinguishable from sibling tools such as submit_enquiry and enquiry_describe through its focus on field metadata.

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 direct usage guidance: pass answers to submit_enquiry keyed by field key. This tells the agent how to apply the returned data and implies the tool is for fetching field metadata before submission. It does not explicitly mention when not to use it or compare with enquiry_describe, but the context is sufficient.

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 delivers: it discloses the two-step validation flow, the return values of step 1 (summary, consent line, confirmation token), the downstream side effects (email with a click-through link before providers see it, details sent to up to three firms), and an opt-out mechanism. This is exactly the behavioral context an agent needs to drive a consent-gated mutation.

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 purpose and the negative scoping before the step-by-step flow; each sentence carries procedural weight. It loses a point for repeating the full consent sentence verbatim from the schema, which is redundant text an agent already has.

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 exists, and the description compensates by naming exactly what step 1 returns and what the end state is (submitted enquiry plus a verification email). For a nested-object, consent-gated tool, 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?

Schema description coverage is 100%, so the baseline is 3, but the description goes further: it ties 'answers' to field keys from the sibling enquiry_fields, states consent=true for both steps, and clarifies that 'confirmation' is the token returned by step 1 used only on the second call. That sequencing meaning is not derivable from the schema alone.

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') and immediately scopes it against the sibling 'calculate' by ruling out a purchase or guaranteed quote. An agent can distinguish this from the other calculator siblings without opening a 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 explicit when-to-use conditions for both calls: step 1 with answers+consent=true, step 2 only 'if the person agrees' with the token, and names the sibling 'enquiry_fields' as the source of field keys. It also states when-not ('NOT a purchase'), leaving nothing to inference.

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