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

Annotations already declare non-read-only, non-idempotent, non-destructive and closed-world, and the description usefully adds the duplicate-refusal rule, the 5-open-quote free limit, and that currency/VAT/issuer are inherited from the shared profile. However, it also asserts prices are in MAJOR units, which conflicts with the schema's unit_price_minor semantics, so the behavioral guidance is actively risky on the most error-prone field.

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?

Four short, front-loaded sentences covering action, money/currency provenance, duplicate rule and quota; no filler or repetition of schema fields. The only wasted space is the incorrect MAJOR-units clause, which actively harms rather than pads.

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 12-parameter creation tool with no output schema, the description covers the return summary (Q number, VAT, totals), quota and duplicate behavior, which is decent. It omits the lifecycle state of the created quote and next-step tools (quote_send_text, quote_pdf, quote_accept), and the units contradiction leaves the most consequential parameter ambiguously specified.

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 would be 3, but the description contradicts the schema: it says "unit_price is in MAJOR units" while the only price field is unit_price_minor, documented as "9000 = 90.00 EUR ... Never a decimal". An agent following the description would submit prices 100x too large. The profile-derived defaults for currency, VAT and issuer are the only genuinely additive semantics.

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?

"Store a quote for client from items and return its Q number, VAT and totals" gives a concrete verb (store/create), the resource (quote), the required inputs and the return payload, so an agent knows this is the creation path. It does not name quote_update or quote_get as the alternatives, so the contrast with siblings is left implicit.

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?

Usage is implied by "store a quote ... from items", and two useful operating constraints are given: duplicates of an open quote are refused, and the free tier allows 5 open quotes. There is no explicit statement of when to call this versus quote_update, quote_get or quote_list, and no prerequisite about the client already existing.

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