site

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

With no annotations, the description carries the full burden; it does disclose one behavioral trait (default fallback) and the computed outputs. It does not explicitly state that this is a read-only calculation with no side effects, but the calculator framing makes that the reasonable reading.

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, front-loaded with the verb and resource, and the fallback behavior is a useful addition. The duplicated 'calculator' is a minor editing flaw but does not obscure meaning.

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?

All five parameters have full schema documentation, and the description names the four output categories, compensating for the missing output schema. It lacks usage/exclusion guidance and exact calculation details, but for a straightforward calculator with documented defaults this is nearly 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?

Schema coverage is 100%, so the schema already documents all five parameters. The description adds no parameter-level meaning beyond what the schema provides, which is acceptable given the high coverage.

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 the exact operation and resource: it runs the Australian employment cost calculator and enumerates its four outputs. This clearly differentiates it from the describe/enquiry siblings, which have no calculation role.

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 sentence telling an agent when to choose calculate over calculator_describe or the enquiry tools. The purpose is clear but the decision context is left entirely 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. It says the tool 'takes' and 'returns' information, implying it is a read-only documentation tool, but it doesn't explicitly state there are no side effects or that it is safe to call. It also doesn't disclose any rate limits or auth requirements. The description gives a decent overview of content but lacks explicit behavioral disclosure.

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 that is concise and front-loaded with the core purpose. It doesn't waste words, but it could be slightly more specific about the tool's output (e.g., that it returns a textual explanation). It is appropriately sized for a simple documentation tool.

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 there is no output schema, the description should explain what the tool returns. It says 'the outputs it returns' but that refers to the calculator's outputs, not the tool's own output. The agent might wonder whether the tool returns a formatted document, a list, or something else. The description is incomplete on this point, and there are no sibling hints about the output format.

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 provides no parameter details. The description mentions the inputs the calculator takes, but that's about the calculator, not the tool's own inputs. Since there are no parameters, the description doesn't need to add parameter semantics; a baseline of 4 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 states that the tool provides information about the calculator's inputs, outputs, assumptions, and tables, which is a clear purpose. It is specific enough to distinguish it from the 'calculate' sibling, which likely performs calculations, but it doesn't explicitly name the sibling alternatives, so it misses a point 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?

No guidance is given on when to use this tool versus the siblings. It doesn't say 'use this before calculating' or mention any alternatives. The agent is left to infer that this is for documentation, but no explicit context is provided.

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. It discloses what the tool returns: the details, consent wording, and confirmation method, and states there is no purchase or guaranteed quote. This gives the agent a clear picture of the tool's output and non-side-effect nature, though it doesn't explicitly state it's read-only (but that's implied).

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 three sentences, front-loaded with the directive 'Read first', and each sentence adds information: what it does, what it doesn't do, and what it returns. It is efficient without being overly terse, though the title already conveys some of the same information.

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 fully covers what the agent needs to know: the purpose, the behavior, and the return content. It is complete for a descriptive tool that is meant to be read before acting.

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 doesn't need to explain parameters, and it doesn't add anything about them, which is appropriate. The schema already shows no properties, so no gap exists.

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 'states plainly what submit_enquiry does', identifying the specific resource (submit_enquiry) and the action (describing/explaining). It distinguishes itself from siblings like calculator_describe by referencing a distinct target tool, so an agent knows exactly what this tool is for.

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' provides a clear directive to use this tool before submit_enquiry, establishing a usage sequence. It does not explicitly mention alternatives or when not to use it, but for a descriptive tool, the implied context is sufficient. It could have named calculator_describe as a parallel for other workflows.

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 burden: it discloses the full return payload (key, label, type, required, help text, options) and the fact that the output is keyed by field key, implying a map structure. There are no side effects or parameters to warn about, so the main missing context is limited to non-essential details like ordering or staleness.

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, under 40 words, with the core content enumeration in the first sentence and the actionable downstream use in the second. 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 introspection tool with no output schema, the description covers the essentials: what is returned, the constituent attributes, and how the output connects to submit_enquiry. Minor gaps such as the exact JSON shape or whether help text is always present are acceptable 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 and an empty schema, so there is no input semantics to document; the 0-parameter baseline of 4 applies. The description adds useful meaning by clarifying that the field keys it returns are the keys used to submit answers to submit_enquiry.

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 precise resource and content set — 'Every field of the Employee Cost Australia enquiry: key, label, type, whether required, help text and the allowed options' — so an agent knows exactly what the tool returns. It differentiates from siblings by focusing on field-level metadata rather than enquiry-level description, and it references submit_enquiry as the consumer of the keys.

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 downstream instruction: 'Pass answers to submit_enquiry keyed by field key,' which tells the agent when this tool matters — as a precursor to submitting answers. It does not, however, name alternatives or state when not to call it, such as contrasting with enquiry_describe.

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 well: it discloses that step 1 only validates (no submission), that step 2 triggers an email-verification link before any provider sees the data, and that contact details go to up to three third-party accountants/payroll providers. It stops short of failure modes (what happens on a rejected validation), idempotency of a repeated step 2, or any withdrawal/retraction behavior after submission.

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 scope disclaimer and the two-step flow, and most sentences carry operative detail. The one waste is the full consent sentence quoted verbatim, which duplicates the consent property's schema description almost word-for-word at roughly 45 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?

There is no output schema, and the description compensates by naming what step 1 returns (summary, consent line, confirmation token) and what step 2 produces (submitted enquiry plus a verification email). Nothing essential for correct invocation is missing, though it never states the step-2 result payload or error 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?

Schema coverage is 100%, so the baseline is 3; the description goes beyond it by explaining the sequencing semantics of 'confirmation' (it comes only from step 1 and is only passed on the second call) and by tying 'answers' to the field keys produced by enquiry_fields. The consent text is only restated, not enriched 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?

States a concrete verb+resource ('Submits an enquiry to Employee Cost Australia') and immediately rules out the two things an agent might confuse it with: 'NOT a purchase, NOT a guaranteed quote.' This lets an agent separate it from siblings like calculate/enquiry_fields 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 an explicit, ordered when-to-use: step 1 with answers+consent=true, step 2 only 'if the person agrees' with the same answers plus the token. It references enquiry_fields for field keys but never states when to prefer enquiry_fields or enquiry_describe, so the alternative-routing guidance is partial rather than complete.

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