site

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 adds transparency by stating that missing inputs fall back to defaults and by listing the specific rates and cost components. It does not describe the return format, side effects, or whether this is a purely computational read-only operation, 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 appropriately short and front-loaded with the action and outputs. However, the doubled 'calculator calculator' is a structural flaw that hurts readability. Each clause adds value otherwise, and the fallback note is useful.

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 calculator tool with five optional, well-documented parameters and no output schema, the description is mostly complete. It lists what the tool computes, gives rates, and explains fallback behavior. It does not explicitly state the exact return payload, but the enumerated outputs give enough context for an agent to invoke it 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 description coverage is 100%, so the baseline is 3. The description adds meaningful context beyond the schema by naming the specific rates (15% NI, 0.5% levy) and the 'True annual cost' output, which helps an agent understand how parameters like salary and pensionRate contribute to the result. The fallback-to-defaults statement also clarifies parameter behavior.

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 clear action ('Run the Employer cost calculator') and resource ('Employer cost calculator'), and enumerates the computed outputs: Employer National Insurance (15%), Employer pension, Apprenticeship levy (0.5%), and True annual cost. It is distinct enough from sibling tools like 'calculator_describe' and 'submit_enquiry', though the phrase 'calculator calculator' is a minor redundancy.

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 when to use the tool: when you need employer cost calculations. It also provides useful guidance that missing inputs fall back to documented defaults, which tells an agent which parameters can be omitted. However, it does not mention alternatives or explicitly say when not to use this tool versus siblings.

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, the description carries the full burden and does so well: it explicitly states that nothing is bought, ordered, or paid, that no quote is guaranteed, and that it is free. It also discloses what the return contains (who receives details, consent wording, confirmation method). It stops short of stating the tool itself is read-only, but 'Read first' and the descriptive tone imply an informational, side-effect-free operation.

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: 'Read first' immediately signals priority, followed by a clear explanation, key caveats, and output details. Every sentence earns its place without redundancy.

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 is complete. It explains the tool's purpose, key behavioral constraints (free, no purchase, no guarantee), and what the returned description includes, leaving no critical gap for an agent deciding whether and how to call it.

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 to explain. The description appropriately omits parameter details and focuses on behavior and output, matching the baseline for zero-parameter tools.

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 opens with 'Read first' and 'States plainly what submit_enquiry does on Employer Cost Calculator' – a specific verb (states) and resource (submit_enquiry). It clearly differentiates itself from submit_enquiry, which actually initiates the enquiry, and lists the content of the returned explanation, making its function unmistakable.

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 directs the agent to use this tool before submit_enquiry, establishing it as a prerequisite. It doesn't name or contrast with siblings like calculator_describe or enquiry_fields, but the focus on submit_enquiry makes the intended use case 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 must convey behavior itself. It states exactly what information will be returned for each field and implies a read-only listing operation. It does not discuss edge cases like missing help text or response format, but for a simple introspection 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?

The description is two sentences, front-loads the tool's purpose, and ends with a useful workflow note. There is no redundant wording.

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 parameters and no output schema, the description provides enough detail about what fields are included and how the output connects to submit_enquiry. An agent can invoke and use the result without additional assumptions.

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?

There are no parameters, so the description has nothing to explain about parameters. It adds value by explaining that the output's key field is meant to be used with submit_enquiry, which is useful contextual 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 identifies the tool as providing every field of the Employer Cost Calculator enquiry, including key, label, type, required flag, help text, and options. It is specific about the resource and content, though it does not explicitly name sibling enquiry_describe as a contrast.

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 gives a clear usage pointer: obtain the fields and then pass answers to submit_enquiry keyed by field key. It does not describe exclusions or compare with enquiry_describe, but the intended workflow is evident.

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?

There are no annotations, so the description carries the full behavioral burden — and it does so thoroughly. It discloses that the first call only validates and returns a token, that the second call actually submits the enquiry, and that no provider sees the enquiry until the person clicks a link in the email. This is rich, honest 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 dense but well-organized: it front-loads the purpose and exclusions, then walks through the two steps in order. Every sentence earns its place by conveying a constraint, a required action, or an important behavioral detail.

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?

With no output schema, the description provides enough detail about expected returns and outcomes: Step 1 returns a summary, consent line, and confirmation token; Step 2 results in submission and an email link that must be clicked before providers see the enquiry. The two-step workflow and consent condition are fully specified.

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?

Although schema coverage is 100%, the description adds important meaning beyond the schema: answers must be keyed by field key from enquiry_fields, and confirmation must be the token returned from Step 1. It also clarifies that consent=true means the person has read and agreed to the exact data-sharing statement.

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 verb and resource — 'Submits an enquiry to Employer Cost Calculator' — and explicitly distinguishes the tool from a purchase or guaranteed quote. This makes it easy for an agent to understand the tool's core function and separate it from sibling tools like calculate 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 description gives explicit step-by-step usage instructions: call first with answers and consent=true, show the summary, then call again only if the person agrees, passing the confirmation token. It also provides clear when-not guidance: this is not a purchase and not a guaranteed quote.

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