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 explicitly states that 'Missing inputs fall back to their documented defaults,' a useful behavioral trait, and implicitly signals a pure calculation with no side effects. It does not explicitly confirm non-mutating behavior, but the calculator framing 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?

The description is two sentences and front-loads the core action with 'Run...'. The colon-separated list of outputs is dense but informative, and the final sentence about defaults adds value. There is no redundant wording or fluff.

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 is provided, so the description responsibly lists the four computed figures: hire cost per year, salary multiple, AI route year one, and AI route year two onward. However, it does not specify the response structure or formatting (e.g., numbers vs. currency, JSON keys), leaving the output contract somewhat unclear for an agent.

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 documents all 10 parameters with descriptions and defaults, achieving 100% coverage. The description adds only a general note about default fallback, which is already represented by the 'default' fields in the schema. No per-parameter meaning is added beyond 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 opens with a specific action, 'Run the AI against a hire, on the same basis calculator', and enumerates the four outputs it produces. This clearly identifies it as the computational tool and distinguishes it from siblings like 'calculator_describe' and the enquiry-based 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 implies the tool is used for computing cost comparisons, but it does not explicitly state when to use it over 'calculator_describe' or the enquiry tools. There is no mention of alternatives, exclusions, or conditions, leaving usage guidance to inference from the name and output list.

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. It does indicate an informational role by mentioning inputs, outputs, assumptions, and tables, but it never explicitly states that the tool is read-only, performs no computation, or returns a description rather than a calculated result. The agent must rely on the name for this.

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 compact sentence that lists the covered content in a sensible order: inputs, outputs, assumptions, and tables. There is no filler or 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 simple parameterless describe tool, the description names the main content areas well, but it does not explain the output format or how this tool relates to 'calculate'. Since there is no output schema, a bit more about the shape of the returned description would make it fully 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?

The tool has zero parameters, so the baseline is 4. The description adds useful context by noting that the described calculator's inputs include units, ranges, and defaults, which helps the agent understand what kind of specification the 'describe' call will provide.

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 indicates the tool describes a calculator's inputs, outputs, assumptions, and tables, so the general purpose is recognizable. However, it lacks an explicit action verb and does not directly distinguish itself from the sibling 'calculate' or the likely 'enquiry_describe' family.

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 only implied: an agent can infer this tool is for inspecting a calculator's specification rather than performing a calculation, but the description never says when to use it versus 'calculate' or another describe/enquiry tool. No alternatives or exclusions are named.

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, and it does so well by stating that nothing is bought, ordered, or paid, that no quote is guaranteed, and that it is free. It also previews what the tool returns: recipients, consent wording, and confirmation mechanism. It stops short of explicitly saying the describe call itself has no side effects, but the framing makes that clear enough.

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 ('Read first'), then explains behavior and return content. The only minor issue is that 'AI vs Hire' is used without explanation, slightly obscuring a key context term.

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 the tool is a zero-parameter informational helper with no output schema, the description supplies adequate context about what the tool does and what information it returns. It lacks explicit output-format detail, but for a no-arg describe-style tool this is 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 the schema already covers everything (100% coverage), so the description does not need to explain parameters. The baseline of 4 applies because there is nothing for the description to add about 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 clearly identifies the tool as a read-first explainer for what submit_enquiry does, with a specific resource (the enquiry submission flow) and a specific purpose (disclosing behavior before action). It contrasts with submit_enquiry by framing this as the descriptive counterpart, though it does not explicitly name other 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?

'Read first' gives a clear signal that this tool is meant to be consulted before taking action, likely before calling submit_enquiry. It also clarifies what the tool does not guarantee (no purchase, no guaranteed quote), which helps an agent avoid misuse. However, it does not explicitly state when not to use this tool or suggest 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, the description carries the full behavioral disclosure burden. It makes clear this is an informational enumeration of fields, not a mutation or submission, and specifies the exact structural content the agent should expect. It does not mention side-effect absence explicitly, but the wording implies a read-only lookup.

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 sentences, no filler, with the core purpose front-loaded. Each sentence earns its place, and the reference to submit_enquiry gives actionable value 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 tool with no output schema, the description is complete: it names the output fields, hints at the shape of each field description, and explains how the result feeds into the submission flow. Nothing essential for correct use 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 schema is empty and the description needs to add little here. It still adds relevant semantics by explaining that the returned field key should be used when constructing answers for submit_enquiry, which helps the agent understand the meaning of the output key.

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 that the tool exposes every field of the AI vs Hire enquiry and enumerates exactly what each field entry includes: key, label, type, required flag, help text, and allowed options. This clearly distinguishes it from sibling tools like submit_enquiry and 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 description tells the agent to pass answers to submit_enquiry keyed by field key, which establishes the practical workflow for using this tool's output. It does not explicitly contrast with enquiry_describe, but the usage context is clear 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, the description carries the full burden and does so: it discloses that step 1 is a dry-run validation that returns a token, that step 2 actually submits, that an email confirmation link is required before any provider sees the data, and that details go to up to three agencies with notification of each firm. It also spells out the exact scope of consent rather than just saying 'consent=true'.

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 procedure is front-loaded and ordered by step, with the non-purchase framing up front, so an agent can act on the first sentence alone. The main cost is the long verbatim consent paragraph, which largely duplicates the consent parameter's schema description; it is useful for fidelity but is the one section that could be trimmed.

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?

There is no output schema, so the description must describe returns itself — and it does, naming the summary, the consent line and the confirmation token from step 1 and the submission plus email-link flow from step 2. For a nested-object, two-phase write tool with no annotations, nothing an agent needs in order to call 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 adds real value beyond the schema by explaining that 'answers' must be keyed by field key from enquiry_fields and that 'confirmation' comes from step 1 after the person approves the summary. It also ties 'consent' to an explicit, externally-defined agreement rather than leaving it as a bare boolean.

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 AI vs Hire) and immediately bounds it with negations ('NOT a purchase, NOT a guaranteed quote'), so an agent cannot confuse it with a transactional or quoting tool. It also implicitly positions itself against siblings enquiry_fields and enquiry_describe by naming 'field key from enquiry_fields' as its input source.

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 gives an explicit two-step procedure: step 1 with answers+consent to get a summary/consent line/token, step 2 only if the person agrees, re-sending answers, consent and the token. The gating condition ('only if the person agrees') and the downstream requirement (the person must click an emailed link before providers see it) are spelled out, 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.