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 two-call validation/submission split, that nothing reaches providers until an email link is clicked, who receives the contact data (up to three Canadian firms chosen by the service), and the exact consent semantics. Side effects and the human-confirmation gate are unambiguous.

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 purpose and non-purchase caveat, then sequenced as Step 1 / Step 2, which matches the calling order. It loses a point because the full consent sentence is repeated verbatim from the consent parameter description, which is redundant text rather than new information.

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?

Despite having no output schema, the description spells out what step 1 returns (a summary, the consent line, a confirmation token) and what happens after step 2 (an email with a click-through link before providers see anything). Nothing an agent needs to drive this multi-call mutation 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; the description earns above baseline by explaining the role each parameter plays in the flow — answers must be keyed by enquiry_fields keys, consent=true is required at both steps, and confirmation is the token returned by step 1 and only sent on step 2.

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 Canada Payroll Calculator') and immediately negates the two most likely misreadings: 'NOT a purchase, NOT a guaranteed quote'. That framing lets an agent distinguish it from calculate and calculator_describe without opening any schema.

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: step 1 with answers + consent=true to validate and obtain a token, step 2 only after the person agrees, with the token. It also names the sibling that supplies input shape ('keyed by field key from enquiry_fields') and states the gate condition for the second call.

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