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 that step 1 only validates and returns a summary/token, that the real submission happens in step 2, that the person must click an emailed link before any provider sees the data, and that details go to up to three named brokers with opt-out rights. These downstream effects and consent requirements are exactly the behavioral context an agent cannot get from the schema.

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-loads the critical 'NOT a purchase' scoping and structures the rest as Step 1 / Step 2, which maps cleanly onto the call sequence. The verbatim consent text is long and duplicates the schema's consent description almost word-for-word, which is the one place the definition could be trimmed.

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 no output schema, the description explains what each call returns (summary, consent line, confirmation token) and what the end state is (email with a verification link). It stops short of describing what happens when validation fails or whether a retried step 1 creates duplicate state.

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 description coverage is 100%, so the baseline is 3; the description earns above that by explaining that answers are keyed by field key drawn from enquiry_fields, that consent=true encodes a specific agreed statement, and that the confirmation token is only required in step 2 — a conditional requirement the schema (which lists confirmation as optional) does not express.

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 Motor Trade Insurance Compare) and immediately rules out the two things an agent might confuse it with: a purchase and a guaranteed quote. The distinction from the compare_* siblings is implicit in the routing language ('keyed by field key from enquiry_fields'), and the two-step framing makes the tool's role unmistakable.

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?

Explicitly prescribes when to call in step 1 (answers + consent=true) and when to call in step 2 (only if the person agrees, with the confirmation token). The gating condition is stated as a rule, not left to inference, and the instruction to show the summary and consent line tells the agent what to do between calls.

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