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: validation happens server-side, step 1 returns a summary/consent line/token, submission is gated on a support-confirmed token, and the person must click an emailed link before any provider sees the data. It also spells out exactly what consent authorizes (up to three assessors, stopping further disclosure), which is unusually rich causal context.

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 core action and the negative qualifiers, then the two steps in order, so structure is strong. It loses a point only because the full consent sentence is reproduced verbatim in both the description and the consent parameter schema, a redundancy that inflates length.

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, yet the description explains what step 1 returns (summary, consent line, confirmation token) and what the end state is (email link, provider visibility gated on click). For a nested-object, two-phase submission tool with no annotations, 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, but the description adds real meaning: answers are keyed by field key sourced from the sibling enquiry_fields tool, consent must be paired with consent=true, and confirmation is the token returned in step 1 only after the person approves the summary. That clarifies the lifecycle and cross-tool dependency beyond the schema text.

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+resource (submit an enquiry) plus scope qualifiers that distinguish it from siblings: it is not a purchase and not a guaranteed quote at Legionella Assessment Cost. An agent can tell it apart from enquiry_describe and enquiry_fields, which only supply field metadata.

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 condition for each call: step 1 with answers + consent=true, step 2 only if the person agrees, re-sending answers, consent and the step-1 token. It also sets exclusions up front ('NOT a purchase, NOT a guaranteed quote'), leaving no inference about when to invoke it.

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