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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=true, but the description adds substantial side-effect context: a two-step flow where voidjet emails the user a link, Villiers only receives the request after the user submits the form within 48 hours, and confirmed options arrive by email. That is meaningful disclosure beyond the annotations. It stops short of covering failure modes or what the tool returns on submission, so a 4 rather than a 5.

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 preconditions are front-loaded and no sentence is filler; the flow explanation earns its place. However, several clauses are packed into run-on sentences, making the middle section denser than it needs to be.

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 values need not be described, and the description fully covers the asynchronous request flow and its timing constraint. The remaining gap is semantic coverage for the undocumented parameters (locale, flexible, passengers, departure_date) on a 10-parameter tool.

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 30% across 10 parameters. The description clarifies that name, phone and message are optional and come from the user, and ties origin/destination to the charter_alternative route, but leaves locale, flexible, passengers and departure_date unexplained in both schema and description. Partial compensation only.

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 ('Requests confirmed charter prices from partner Villiers for the route of a charter_alternative') and explicitly distinguishes itself from the empty-leg siblings with 'NOT an empty leg: a regular charter and a paid partner offer.' An agent can identify the operation and its scope without opening the 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?

Gives an explicit precondition set (user has seen the price range, asked for confirmed prices, and supplied their email) and an explicit exclusion (not an empty leg, which routes the agent toward get_empty_leg/search_empty_legs). Both when-to-use and when-not-to-use are stated.

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