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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts beyond that: nothing is persisted or dispatched, no authentication is required, the endpoint is rate limited, and currency is treated as an opaque label with no FX conversion.

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 dense sentences with no filler, and the core capability plus calculation model is front-loaded before the boundary and constraint statements. Every sentence carries information, though the constraint list reads slightly as a run of short fragments.

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?

An output schema exists, so return-value description is rightly omitted, and the calculation and boundary behavior is covered. The gap is input completeness: with five required parameters and zero schema descriptions, the description leaves sender, client, quotationNumber, and the line-item array shape entirely to inference.

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 0%, so the description carries the full burden and only partially meets it. It usefully defines discount as a percentage per line item and tax as applied to the already-discounted amount, and clarifies the currency field's semantics, but says nothing about quotationNumber, sender, client, or the lineItems array limits.

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: generate a quotation JSON and plain-text draft, with the calculation model spelled out (per-item percentage discounts, tax on discounted amounts). This clearly separates it from document-oriented siblings like sow_generate or retainer_agreement, though it never names those siblings explicitly.

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 negative boundaries are stated ('does not save, send, or render PDF; website provides visual export'), which tells the agent this is a data-draft generator rather than a delivery pipeline. However, no alternative tool is named for any of those downstream needs, and no prerequisites or when-to-prefer-this-over-siblings guidance is given.

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