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 write/consent boundary, the double opt-in (the person must click an emailed link before any provider sees the enquiry), that details go to up to three firms chosen by the calculator, and that the person can stop further firms receiving details. It also names the three return artifacts of step 1 (summary, consent line, confirmation token).

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 key disambiguation ('NOT a purchase') is front-loaded and the two steps are ordered and labelled. The full consent text is quoted verbatim and partly duplicates the schema's consent description, which is justified only because the agent must show that exact line to the person, but it does add 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 and what happens after step 2, so the agent knows the full lifecycle before and after the call. For a two-phase, consent-gated submission tool with a nested object parameter, the coverage of flow, prerequisites and outcome is sufficient to invoke it correctly.

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' is keyed by field key from the enquiry_fields sibling, 'consent' must be true only after the person has agreed, and 'confirmation' is the token produced by step 1 after approval. Only the shape of the answers values is left to the schema.

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 states a specific verb (submits) and resource (an enquiry to human providers), and immediately draws the boundary that matters most: 'NOT a purchase, NOT a guaranteed quote.' It is clearly distinguishable from calculate, calculator_describe, enquiry_describe and enquiry_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?

It spells out an explicit two-step protocol: step 1 is called with answers plus consent=true to validate, step 2 is called 'only if the person agrees' with the same answers plus the confirmation token. The preconditions for each call and the human-approval gate between them leave nothing to inference.

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