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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered upstream. The description still adds real value beyond them: quote_id lasts 24 hours and is bound to the dataset version, and nothing is charged. The PECR/GDPR paragraph is genuine behavioral context about what the quote excludes (sole traders and ordinary partnerships by default), though the "unless the toggle is changed" reference is unactionable because no such parameter exists in 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?

Purpose and cost/expiry facts are front-loaded in the first two sentences, and the next-step instruction follows logically. The final sentence is a dense, comma-spliced legal disclaimer (Article 6(1)(f), PECR, subscriber categories) that is informative but heavier than the rest and slightly slows scanning.

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 tool has an output schema, so return values need not be described. What remains that an agent needs before calling is all present: cost (free), account requirement (none), quote lifetime and version binding, the correct follow-up call, and the audience-composition caveat that affects what the quote counts.

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 description coverage is 100%, so every parameter is already documented in the schema, which sets the baseline at 3. The description adds conceptual framing ("removing ones already held and suppressed" maps to dedupe_against, and it lists licence and warranty as quote components) but no syntax, defaults or format detail beyond what the schema supplies.

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 opening clause names the verb and the resource precisely ("Creates a machine quote for a count") and immediately enumerates what the quote contains: deduped record counts, credits and GBP price, licence, warranty, blockers. It also explicitly separates itself from the similarly named human sales quote ("a 14 day PDF made in the app"), so an agent can tell the two apart without inspecting schemas.

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 workflow: "Show the credits and price to the user, then call create_order with the quote_id", which names the sibling and the condition that selects it. It also states a when-not (do not expect a human sales quote) and clarifies no account or payment is required, removing the main hesitation an agent might have before calling a pricing tool.

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