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

Goes well past the annotations (readOnly=false, destructive=false, idempotent=true, openWorld=true) by disclosing the full lifecycle: nothing is charged, the traveller receives an e-mail request, the driver confirms or declines, and payment of a 30% deposit is described in the confirmation. It also explains idempotency scope (same request within a day, or same requestId, returns the same reference), that only valid requests count against limits, the shape of a refusal (named argument plus retryAfter), and that dry_run validates and prices without sending.

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 critical information (what it sends, what it costs, dry_run) is front-loaded, but the whole definition is a single dense run-on paragraph mixing flow description, idempotency, and error handling. One clause is garbled ('next says it for this request'), costing clarity, and the mode enumeration would read far better as a list.

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 32-parameter mutation tool with no annotations for safety nuances and no output schema, the description covers the important gaps: three request shapes, dry_run, deduplication, error/refusal format, and rate-limit recovery. It stops short of describing the returned reference object's shape, though 'answers the same reference' hints at it.

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 only 28% across 32 parameters, but the description compensates for the highest-value ones by grouping them into modes (quote fields for one service, 'items' for up to several, package+startDate for a plan) and explaining dry_run and requestId. Many parameters (guests, luggage, car, option, stops, returnTrip, extraHours, direction, returnFlight) get no semantic help beyond the schema.

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?

Opens with a specific verb+resource ('Sends a booking request') and immediately enumerates the three supported shapes: a single service mirroring quote's fields, 'items' for several, and a find_packages plan plus startDate. An agent can distinguish it from quote (pricing) and find_packages (plan discovery) without opening any schema.

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?

States the precondition clearly ('once the traveller has seen the price and accepted the terms of sale') and offers dry_run as the non-committing alternative for checking and pricing. It does not explicitly say 'use quote first' or list when-not-to-use, so a small inference gap remains.

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