site

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

With no annotations, the description carries the burden and does well: it states that nothing is bought, ordered, or paid, that no quote is guaranteed, that the process is free, and that the tool returns recipient details, consent wording, and confirmation behavior. It stops slightly short of explicitly saying that calling enquiry_describe itself has no side effects, though 'Read first' and the descriptive verb make 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-loaded with 'Read first,' immediately telling the agent how to use it. Every sentence adds value: it states what the tool explains, clarifies the non-committal nature of the submission, and lists the returned information. No filler or unnecessary 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?

For a no-input, no-output-schema documentation tool, this description is complete. It tells the agent what the tool is for, what important caveats to surface, and exactly what information the call returns. Nothing needed to safely invoke or interpret the result 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 and the schema already covers the input completely, so the description has no parameter burden. The baseline of 4 applies because with no parameters there is nothing the description needs to compensate for.

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') and resource ('what submit_enquiry does on Commercial Kitchen Cost'), making it clear this is an explanatory/read-first tool rather than the actual submission action. It distinguishes itself from the sibling submit_enquiry by explicitly discussing that tool and from enquiry_fields by focusing on behavior rather than fields.

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' clearly tells the agent to consume this description before invoking submit_enquiry, and it names the underlying action it explains. It does not explicitly enumerate when to use enquiry_fields versus this tool, but for a read-first explainer the usage context is strongly implied.

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 present, so the description carries the full burden. It discloses what data is exposed and how it should be used, but it never explicitly states that invoking this tool is a read-only, side-effect-free lookup; that is left to inference from the field-metadata framing.

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 tightly written sentences cover both the output content and the downstream usage. The core statement about every field is front-loaded, and no filler or redundant schema repetition is present.

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 output schema, the description enumerates the returned field attributes and links them to the sibling submission flow. It is complete enough for a simple metadata lookup, though an explicit statement of the output shape or read-only nature would make it fully unambiguous.

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 is no parameter ambiguity; the baseline for this case is 4. The description adds useful semantic context by explaining that field keys from this tool are the identifiers to use when calling 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 clearly states that this tool exposes every field of the Commercial Kitchen Cost enquiry, along with key, label, type, required flag, help text, and allowed options. It does not use an explicit verb like 'returns' and does not distinguish itself from the sibling enquiry_describe, so it falls just short of a 5.

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 instruction to pass answers to submit_enquiry keyed by field key gives clear downstream context for when this tool's output is needed. It does not explicitly name alternatives or exclusion conditions, but the context is clear enough for an agent to know this is a prerequisite for building a submission.

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 the non-purchase/non-quote nature, that step 1 only validates and returns a summary/consent line/token, that step 2 is irreversible submission, that an email confirmation click is required before any provider sees it, and the exact scope of consent (up to three fit-out firms, notification per firm, ability to stop). That is far beyond what any annotation 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?

Front-loaded with the most important constraint (not a purchase) and cleanly numbered into Step 1 / Step 2, so an agent can parse the sequence at a glance. It loses a point for restating the long consent sentence that already appears verbatim in the consent parameter description.

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 describing exactly what step 1 returns (summary, consent line, confirmation token) and what the person receives afterward. For a consent-gated, two-phase write operation with nested answers and 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 coverage is 100% and the consent text is duplicated verbatim from the schema, so the baseline is 3. The description nonetheless adds workflow meaning the schema cannot: answers must be keyed by field keys from enquiry_fields and must be re-sent identically in step 2, and the confirmation token is only supplied on the second call after approval.

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 Commercial Kitchen Cost') and immediately bounds it with two explicit negations ('NOT a purchase, NOT a guaranteed quote'). It also ties itself to the sibling enquiry_fields by naming it as the source of the field keys, so an agent can distinguish it from enquiry_describe/enquiry_fields without opening schemas.

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 protocol: step 1 with answers and consent=true, then step 2 only 'if the person agrees', with the same answers plus the confirmation token. It also names the prerequisite (field keys come from enquiry_fields) and the gating condition (the person must click the emailed link before providers see anything).

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