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 validates and returns a summary, consent line and confirmation token; that Step 2 actually submits; and that a confirmation email link must be clicked before any provider sees the details. It also reproduces the exact consent text and what consent authorizes.

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 essential framing (what it is, what it is not), then Step 1, Step 2 and the consent definition in order. The long verbatim consent quote is repeated from the schema, which costs some redundancy, but it is legally load-bearing text and the surrounding prose stays tight.

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?

No output schema and no annotations, so the description must explain outcomes itself — it names the Step 1 return values, the Step 2 side effect, and the email-verification gate. For a nested-object, multi-step mutation tool this is complete enough to call 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 all three parameters are already documented, setting the baseline at 3. The description adds operative meaning beyond the schema: that answers should be keyed by field key from enquiry_fields, that consent=true is mandatory at both steps, and that confirmation is the token carried over from Step 1.

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 Employee Cost Calculator NZ") and immediately scopes it against likely misreadings ("NOT a purchase, NOT a guaranteed quote"). The two-step framing and the note that providers only see it after email confirmation make its identity distinct from the sibling calculate/enquiry_* tools.

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 sequences usage: Step 1 is called with answers + consent=true, Step 2 "only if the person agrees" with the confirmation token. That condition is a genuine when-to-use rule. It stops short of naming alternatives (enquiry_fields, enquiry_describe) as the source of answer keys, so the agent must infer that linkage.

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