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

With no annotations provided, the description carries the full behavioral burden and exceeds it. It discloses non-obvious traits: the first call does NOT submit anything but validates and returns artifacts (summary, consent line, token); the second call triggers an email containing a link that must be clicked before any provider sees the enquiry; and it quotes the exact consent text the person must agree to. This is precisely the side-effect and sequencing information an agent cannot infer from the schema.

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 long but dense, and the most critical caveats ('NOT a purchase, NOT a guaranteed quote') are front-loaded before the procedural details. The step-by-step structure is clearly labeled (Step 1, Step 2), and the quoted consent line earns its place because it is the exact agreement the agent must verify. It could be tightened slightly, but no sentence 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?

For a tool with no annotations and no output schema, the description is remarkably complete. It explains what step 1 returns (summary, consent line, confirmation token), what step 2 does (submits, sends email with click-required link), and the consent precondition — everything an agent needs to execute the flow correctly. The only omissions are error/failure behaviors, which are minor against the thorough procedural coverage.

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, but the description adds meaningful context on top: it says answers are 'keyed by field key from enquiry_fields' (linking the parameter to its sibling tool), and it explains that the confirmation parameter belongs only to the second call 'after the person has approved the summary.' This connects each parameter to the step in which it is used, which the schema alone does not convey.

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 Asbestos Disposal Cost') and goes further by defining the tool's scope: it is explicitly 'NOT a purchase, NOT a guaranteed quote' and is a two-step process. The verb 'submit' clearly differentiates it from the read-only siblings enquiry_describe and enquiry_fields, and the workflow description leaves no ambiguity about what this tool accomplishes.

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?

Provides an explicit, actionable protocol: call once with answers and consent=true, then call again 'only if the person agrees' with the same answers, consent=true and the confirmation token. It also references enquiry_fields as the source for answer keys, implicitly routing the agent to the correct sibling for preliminary data, and states the condition under which submission proceeds.

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