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

No annotations are present, so the description carries the full burden, and it acquits itself well: it discloses that step 1 only validates and returns a summary/token, while step 2 is the actual submission; it states the email-with-link requirement and that providers see nothing until the link is clicked. It also defines consent verbatim, removing ambiguity about what the person must agree to. This is unusually transparent.

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 roughly 120 words but is structured as numbered steps and a quoted consent statement, so it is easy to parse. The 'not a purchase/not a guaranteed quote' disclaimer is front-loaded, and every sentence adds necessary operational or safety context. The length is justified by the two-step complexity.

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?

The description fully explains the two-step lifecycle, the validation output of step 1, and the submission effect of step 2, including the email-link gate. The only gap is that the return value of step 2 (e.g., a success confirmation) is not described, and with no output schema the agent must infer it. Minor but worth noting.

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?

The input schema already covers the three parameters competently (100% description coverage), including the consent wording and the confirmation token's origin. The description adds the crucial temporal relationship: answers must be identical across both calls, consent must be true in both, and the confirmation token is obtained in step 1 and used only in step 2. This exceeds the baseline but doesn't drastically rewrite 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 uses a specific verb and resource: 'Submits an enquiry to EPC Upgrade Cost', and immediately disambiguates 'NOT a purchase, NOT a guaranteed quote'. The two-step mechanism and the reference to enquiry_fields make it distinct from its siblings. An agent will not confuse it with enquiry_describe or enquiry_fields.

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 provides an explicit two-step protocol: call first with answers and consent=true to obtain a confirmation token, then call again with the same answers, consent=true, and the token only if the person agrees. It also states what the tool is not (not a purchase, not a guaranteed quote), giving a clear when-not boundary. While it doesn't compare directly to enquiry_describe or enquiry_fields, it points to enquiry_fields for keying answers, which is sufficient for this context.

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