Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations supplied, the description carries the full burden and does so: it discloses that step 1 only validates and returns a summary/consent line/token, that submission triggers a double opt-in email the person must click before any provider sees the data, and that details go to up to three suppliers who contact them directly. It also spells out the exact consent semantics and the opt-out right, which is behavior an agent cannot infer anywhere else.

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 most important disambiguation ('NOT a purchase') and organized as Step 1 / Step 2, which maps directly onto how the agent must call it. It loses a little efficiency by reproducing the full consent paragraph verbatim, which is already present in the schema's consent parameter description.

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 mutating, two-phase, human-consent-gated tool with no annotations and no output schema, the description covers the return values of step 1 (summary, consent line, token), the post-submission email flow, and the data-sharing scope. Nothing an agent needs to invoke it correctly or explain it to a person 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 goes beyond it by explaining that answers must be keyed by field key sourced from enquiry_fields, that consent=true is only valid once the person has agreed to the quoted text, and critically that confirmation is supplied only on the second call with the answers resent unchanged. That sequencing constraint is orchestration knowledge absent from the schema itself.

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?

Names a specific verb and resource ('Submits an enquiry to HACCP Software Compare') and immediately disambiguates with 'NOT a purchase, NOT a guaranteed quote', which is the key distinction an agent needs. The two-step structure is stated up front, so the tool is clearly separable from siblings like enquiry_fields and compare_options.

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 explicit when-to-call conditions for both steps: step 1 with answers + consent=true, then step 2 only 'if the person agrees', with the same answers plus the confirmation token. It also names the prerequisite dependency on enquiry_fields for obtaining field keys, and the human-approval gate that must be satisfied before submission.

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