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 validation/summary/token return of step 1, that submission only happens on the second call, that a double opt-in email link must be clicked before any provider sees the data, that up to three suppliers receive the contact details, and exactly what consent attests to. Error paths are not described, but the state machine, data-sharing scope, and side effects are unusually well disclosed.

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 disambiguation, then the two steps in order; every sentence is operative. The verbatim consent quote is long and repeats the schema's consent description, which is defensible for a legal attestation but is mild duplication.

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 cover returns, and it does: step 1 yields a summary, consent line and confirmation token; step 2 yields a submitted enquiry plus a person-facing confirmation email. Nested 'answers' keying is also explained ('keyed by field key from enquiry_fields'). Nothing needed to invoke 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, but the description adds sequencing semantics the schema cannot express: 'confirmation' belongs only to step 2 and must be omitted in step 1, and consent must be paired with the displayed summary. The consent wording is largely duplicated from the schema rather than extended.

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 Compare Trade Software') and immediately negates the two most likely misreadings: 'NOT a purchase, NOT a guaranteed quote.' This clearly separates it from the compare_* siblings (which read/compute) and from enquiry_describe/enquiry_fields (which only surface 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 protocol with the gating condition spelled out: step 1 with answers + consent=true, show the person the summary, and step 2 'only if the person agrees' with the token added. It also states the precondition that consent=true means the person has read the quoted consent sentence, leaving no ambiguity about when to call.

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