search_flights

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

With no annotations, the description carries the full behavioral burden and does so thoroughly. It discloses inference rules ('Currency is currency or inferred from a named origin's owned country'), constraints ('must not be guessed'), defaults ('Unnamed baggage_buffer is 0'), and specific behaviors like 'Prefer bags / carry_on on the shopping request' and 'max_stops is 0, 1, or 2.' It also warns about environment requirements for fetch=detail. This goes well beyond a basic mutation hint.

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 description is a dense block of text but every sentence carries useful information. It front-loads the core purpose and alternative routing first, then dives into specifics. It is longer than ideal but not verbose – each clause adds a constraint or default an agent must know. The structure could be improved with bullet points, but it remains efficient and scannable.

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?

Given the tool's complexity (35 parameters, no output schema, no annotations), the description covers many critical aspects: route format, currency/country inference, bag handling, max_stops, and environment prerequisites. It does not describe the return value structure, which is a gap since there is no output schema, and some optional parameters (e.g., 'proxy', 'depart_window') lack explanation. However, the coverage is strong for the most consequential fields, making it largely complete for correct invocation.

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 0%, so the description must compensate. It clarifies key parameters: 'routes' format (ORIGIN-DEST:YYYY-MM-DD), currency inference rules, country as Google gl, baggage_buffer default, and max_stops allowed values. However, many parameters like 'proxy', 'nearby', 'exclude_via', 'depart_window', etc. are left undefined; their titles are self-explanatory or not, and the description doesn't add meaning for them. Partial compensation for a 35-parameter 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?

The description opens with a specific verb and resource: 'Search Google Flights for named routes and dates.' It immediately distinguishes itself from siblings by naming search_dates and search_flex as alternatives for different use cases, so an agent can tell which tool to pick without opening schemas.

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 states when to use alternatives: 'Use search_dates for the cheapest week and search_flex for ±N days.' It also gives prerequisites (fetch=detail requires browser extra and Chromium) and instructs to ask when unsure about currency or country, so the agent knows exactly when to call this tool vs others.

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