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

Annotations cover the write/idempotent/safe profile, but the description adds substantive behavior: the proposal is not binding and stands until the business says yes, non-negotiable pricing is forwarded as a message rather than refused, and frequent or post-round suggestions are passed_on. It stops short of describing the response envelope, but for a no-output-schema negotiation tool the behavioral disclosure is unusually deep.

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 content is front-loaded, but it is delivered as one enormous multi-clause sentence riddled with em-dashes and conditionals, making it hard to scan. Branching logic this complex should be broken into list items rather than a single dense paragraph.

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?

With 9 parameters, nested objects, and no output schema, the description does the heavy lifting by explaining the two negotiation regimes and the fallback path. It omits any description of the success response payload and only hints at the 409 offer_changed case (which the schema documents), but the core decision logic is covered.

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 89% so the baseline is 3, but the description adds real meaning: index 0 drops a line, start_time means a free slot for a booking versus a target time for a quote, quantity is quote-specific, and total_price/unit_price are gated on price_negotiable. These are semantic distinctions beyond the raw field names.

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 states a specific action: answer the business's offer with counter-terms (start_time, quantities, delivery_when, quantity, or a price), and frames it as a request that goes back to the business. This is enough to distinguish it from accept_offer/decline_offer, though it never names those siblings, so the differentiation is inferred rather than explicit.

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?

It lays out explicit branches: free times come from check_availability, a quote time is the time it is for, order changes are indexed in offer.terms.lines, confirmed bookings/accepted orders change orderedItem, and pricing is only an answer where get_business_profile says price_negotiable. It names the sibling tools and the conditions selecting each path, plus the fallback (goes to a person as a message) and never-refused behavior.

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