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

With zero annotations, the description carries the full behavioral burden and succeeds: it discloses the two-step non-atomic behavior, the email side effect, and the material condition that providers only see the enquiry after the person clicks the link. It also states the exact consent wording that must be agreed to. An agent knows precisely what will happen and what constraints apply.

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 description is a single dense paragraph, but every sentence earns its place: exclusions, step 1, step 2, consent text, and post-submission behavior. The most critical discriminator ('NOT a purchase, NOT a guaranteed quote') is front-loaded, and the title summarizes the key facts. It could be improved with explicit numbering to separate step 1 from step 2, but no content is wasted.

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 and no annotations, the description covers everything needed for correct execution: return values from step 1 (summary, consent line, confirmation token), the conditional trigger for step 2, the email-link gating behavior, and the exact consent text. For a high-complexity two-step tool, nothing an agent needs to call it correctly on the happy path 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 schema already documents all three parameters, putting the baseline at 3. The description adds value beyond the schema by explaining that confirmation is only used in step 2 and by clarifying that answers must be keyed by field keys from enquiry_fields. This protocol context enriches the parameter semantics without contradicting 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 and resource ('Submits an enquiry to Oil Tank Removal Cost') and immediately carves out what it is NOT ('NOT a purchase, NOT a guaranteed quote'), which prevents the agent from treating it as a transactional tool. The title reinforces the two-step nature. This is clear enough to distinguish from the enquiry_describe and enquiry_fields siblings.

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?

The description gives an explicit, step-by-step invocation protocol: call once with answers and consent=true to validate, show the summary/consent line, then call again with the confirmation token only if the person agrees. It also names the source of answer keys ('keyed by field key from enquiry_fields'), implicitly pointing to a sibling. It does not explicitly name alternatives or say 'use enquiry_describe when you need to describe the enquiry,' so the routing guidance is strong but not fully explicit.

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