site

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

No annotations are supplied, so the description carries the full burden. It usefully discloses that omitted inputs default rather than erroring, but says nothing about determinism, side effects, currency/units, or how the four figures relate to each other.

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?

It is short and the output enumeration is front-loaded, which is good. But the four-item list reads like scraped output labels rather than a coherent explanation, and the 'calculator calculator' duplication is wasted text.

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 and no annotations, the description does helpfully enumerate the four result figures, which is the right instinct. However, for a computation tool it never states units, currency, or the relationship between the baseline and the ex-gratia/package ranges, leaving meaningful gaps.

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%, with every parameter documented and an enum on circumstances, so the schema does the heavy lifting. The description adds only the default-fallback note, which the schema already encodes via default values; it adds no interpretation of years, salary, or ageBand.

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 ('Run') and resource (Employment settlement calculator) and enumerates the four figures it produces, which tells an agent what it gets back. The duplicated 'calculator calculator' phrasing is sloppy and it makes no attempt to position itself against calculator_describe, but the domain and output are identifiable.

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 statement of when to use this versus calculator_describe, nor any prerequisite or exclusion. The only usage-adjacent information is 'Missing inputs fall back to their documented defaults', which implies you may call it with partial or no arguments but does not frame the decision.

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 carry the behavioral burden. It does disclose the returned content (units, ranges, defaults, outputs, assumptions, tables), which is genuinely useful, but says nothing about the return format, that the tool is read-only and side-effect free, or that it takes no arguments.

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 compact sentence that enumerates the useful content without padding. It is slightly weakened by being a fragment with no leading verb, so the payload is not front-loaded with what the tool actually does.

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, so the description is the only source of return-value information — it enumerates the categories well but not their form (structured vs. prose, static vs. computed) or how an agent should apply them to a subsequent `calculate` call.

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 takes zero parameters and the schema is an empty object, so there is nothing to disambiguate. Baseline 4 applies; the description correctly implies the tool is called without arguments.

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 is a noun fragment listing contents (inputs, outputs, assumptions, tables) rather than a verb-led statement like 'Returns documentation about...'. Combined with the title, an agent can infer this is a describe/metadata tool distinct from the sibling `calculate`, but the inference is required rather than stated.

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 on when to call this versus `calculate` — the obvious pairing in the sibling list. Nothing says whether this should be consulted before invoking the calculator, or that it is a safe read that requires no arguments.

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 provided, so the description carries the behavioral disclosure burden. It clearly indicates the tool is descriptive and read-only ('States plainly', 'returns...'), and it discloses exactly what information is returned: recipients, consent wording, and confirmation method. It also removes risk by clarifying that nothing is bought, ordered, or paid.

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 front-loaded with 'Read first' and every sentence adds meaningful information: action, exclusions, cost, guarantee, and return contents. It is compact yet fully informative.

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 descriptive tool with no output schema, the description covers what the user receives and clarifies the boundary with submit_enquiry. It could be slightly more explicit about the exact format of the returned text, but it is otherwise 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 and schema coverage is 100%, so the baseline is 4. There is nothing for the description to add about parameter behavior, and it does not mislead.

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 is specific: 'States plainly what submit_enquiry does on Settlement Calculator' uses a distinct verb and names its resource. It clearly separates itself from submit_enquiry by being a descriptive explanation rather than the actual action, and from calculator_describe by topic.

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 a direct instruction to invoke this tool before using submit_enquiry, and the body explains the context in which it applies. It does not explicitly name exclusions or alternatives, but the usage intent is 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?

There are no annotations, so the description carries the behavioral burden. It transparently discloses what the tool exposes: every enquiry field with its properties, and it implies a read-only metadata lookup by telling the agent to pass answers to submit_enquiry separately. It does not discuss edge cases or failure modes, but for a simple field-listing 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?

A single, information-dense sentence that front-loads the resource and immediately lists the output attributes. Every phrase earns its place, and the instruction about submit_enquiry is a useful addition without 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 tool, the description is complete: it names the resource, enumerates all returned field attributes, and explains how to use the result with a sibling tool. No critical information 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 baseline is 4. The description adds relevant semantic context by explaining that returned field keys are used to key answers when calling submit_enquiry, which is helpful even though no parameters need documenting.

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 ('Every field of the Settlement Calculator enquiry') and enumerates the available attributes (key, label, type, required, help text, allowed options). It is distinguishable from siblings like calculate and submit_enquiry, though it lacks an explicit verb such as 'returns' or 'lists'.

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 clear context for use: it provides the field metadata needed to construct a payload for submit_enquiry, and explicitly says to pass answers keyed by field key. It does not explicitly exclude alternatives or state when not to use it, but the intended workflow is 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 carries the full burden and does: it discloses that step 1 validates and returns a summary/consent line/token that must be shown to the person, that submission triggers an email with a link that must be clicked before any provider sees the data, that details go to up to three solicitors, and that the person can stop further firms. These are material side effects and a double opt-in gate that no structured field conveys.

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 two disqualifiers and the step ordering, so the critical information is first. It is somewhat long and the consent string is reproduced verbatim in both the description and the schema's 'consent' field, which is the only real 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?

There is no output schema, so the description must explain returns and it does: a summary, the consent line, and a confirmation token in step 1, and an emailed verification link in step 2. For a stateful two-call mutation with nested answer objects, nothing an agent needs 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 coverage is 100%, so the baseline is 3; the description adds genuine flow semantics beyond the schema by tying 'answers' to the sibling enquiry_fields keys and clarifying that 'confirmation' only exists in step 2 after approval. It stops short of describing accepted answer types or validation failure 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?

States a specific verb and resource ('Submits an enquiry to Settlement Calculator') and immediately rules out two plausible misreadings ('NOT a purchase, NOT a guaranteed quote'). It also names the sibling tool that supplies the input shape ('keyed by field key from enquiry_fields'), so an agent can distinguish it from calculate/enquiry_describe 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 two-step invocation protocol with a hard gate between them: step 1 with answers+consent, then 'only if the person agrees' step 2 with the same answers plus the returned token. The agent knows exactly which call to make at which moment and when not to proceed.

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