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

With no annotations, the description carries the full behavioral burden, and it discloses the single most important trait: this tool only generates a pre-filled link and never creates a booking, plus what data is embedded in the link. It does not mention return format or error/failure behavior, which keeps it from a 5, but the highest-risk behavioral fact is front and centre.

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?

Two sentences with zero waste. The core action and beneficiary ('so the traveller only picks the car and pays') are front-loaded, and the critical 'No booking is created' caveat gets its own sentence. Every word earns its place.

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?

Despite 14 parameters, the tool's behavior is simple, and the description covers the purpose, the scope of embedded data, and the non-mutating nature. The main omission is the return shape — there is no output schema and the description never states what is returned, though 'Build a link' strongly implies a URL. Slightly more would make it fully complete.

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 50%, so the description must partially compensate. It enumerates the parameter categories (date, time, passengers, luggage, pickup, drop-off, contact details), covering roughly 10 of 14 parameters, but adds little semantic depth beyond the schema — nothing about coordinates, note, or language interplay. It partially bridges the gap but does not fully compensate for undocumented params.

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 names a specific verb and resource ('Build a link to Tripyana's online booking form'), states what gets pre-filled (date, time, passengers, luggage, pickup, drop-off, contact details), and the 'No booking is created by this tool' clause draws a clear line against booking-creation tools. Among siblings, which are price, info, and search tools, this is unmistakably the link-builder.

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 description conveys a clear use case — when a traveller should finalise car choice and payment themselves — and gives an explicit when-not ('No booking is created by this tool'). It stops short of a 5 because it never names an alternative sibling (e.g., use get_transfer_price for a quote), leaving differentiation to inference.

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