Search flights

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

Annotations already cover readOnly/idempotent/openWorld/destructive, so the bar is lower. The description adds real behavioral context: the price is exactly 'the integer Google returned' and the tool 'does not invent a fare, a flight number, or a bag rule' — a useful data-fidelity guarantee. It omits rate limits or latency expectations.

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 the core purpose in the first sentence, followed by short, scannable points. Slight redundancy with the schema (defaults, IATA/city input) costs it the top score, but nothing is padded.

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 13-parameter tool with an output schema and rich annotations, the description covers the key ambiguities: date-window modes, defaults, and fare provenance. Mutual-exclusion rules (nights vs return_date, depart_date vs from/to) are left entirely to the schema, but the schema handles them well.

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 100%, so the schema already documents all 13 parameters including date formats, mutual exclusions and the 7-date search cap. The description restates defaults (1 adult, economy, CHF) and the accepted origin/destination forms, adding little beyond what the schema provides; baseline 3 applies.

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: 'Search live public Google Flights fares across a short date window.' It also implicitly separates itself from the resolve_airports sibling by noting origin/destination accept city names directly, so an agent knows it need not resolve codes first.

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?

It sketches the planning patterns supported ('one day, a few days around that day, or a from/to window'), which implies usage, but never states when to use this over resolve_airports or when the tool is inappropriate. No explicit exclusions or alternative-routing guidance.

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