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

With no annotations the description carries the full load and does so well: it discloses that step 1 is a validation-only call returning a summary, consent line and token, that step 2 triggers submission and an email, and that a double opt-in click gates provider visibility. It does not cover failure modes — invalid answers, an expired or reused token, or calling step 2 without step 1 — which is the remaining gap for a no-annotation mutation tool.

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 ('NOT a purchase') then organised as Step 1 / Step 2, which is exactly the order the agent needs. It is long and the consent sentence repeats nearly verbatim from the schema, costing some economy, but the bulk of the length is load-bearing consent language.

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 two-phase mutation with a nested `answers` object and no output schema, the description supplies what an agent needs: the return of step 1 (summary, consent line, token), the side effect of step 2 (email with a verification link), and where to get the valid answer keys. Only error/edge-case behaviour is absent.

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 real semantics: `answers` is keyed by field key sourced from enquiry_fields, `consent` must be true in both steps, and `confirmation` is the token returned by step 1 and supplied only after the person approves the summary. That is ordering information the schema alone does not convey.

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?

Specific verb and resource ('Submits an enquiry to Waste Carrier Check') plus explicit negative scoping ('NOT a purchase, NOT a guaranteed quote') that immediately separates it from any checkout or quote tool. It also points at the sibling that defines the answer keys (enquiry_fields), so the agent can identify it against checker_* siblings.

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 two-step protocol is spelled out with an explicit precondition for step 2 ('only if the person agrees') and an explicit precondition for step 1 (answers keyed by field key, consent=true). When-to-use is unambiguous and the branch condition is stated rather than inferred.

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