Kayak MCP

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses why prices are absent (client-side rendering behind bot protection), that the result is a single object never a list, that deep_link equals search_url, and that return_date is null for one-way. These are exactly the failure modes an agent would otherwise hit.

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?

Front-loaded with purpose and the critical 'URL only, no prices' caveat before the details. The inline result-shape enumeration is somewhat redundant against the existing output schema, though the accompanying 'never a list' warning 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?

Complete for a six-parameter link builder: purpose, limits, alternative route, and output expectations are all covered. Because an output schema exists, the result-shape recap is a bonus rather than a necessity, and the anti-pattern warning ('no fares, flights or offers to read') closes the main remaining gap.

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 100%, so the schema already defines all six parameters and their defaults, establishing a baseline of 3. The description adds value beyond that by clarifying the output-side meaning of return_date (null when omitted for one-way), which the schema only frames as an input instruction.

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 first sentence gives a specific verb and resource ('Build a Kayak.com flight-search deep link for a route and dates') and immediately scopes out what it does not do ('no prices'). An agent knows exactly what artifact this produces and where its limits lie 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?

Explicitly routes the agent: 'Open deep_link in a browser for live results, or use google_flights_search for parsed fares.' This names both the correct usage pattern and the alternative tool with the condition that selects it, leaving nothing to inference.

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