explore_destinations

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool returns ('a list of destinations with flight price, hotel price, best travel dates, flight duration, and stops') and describes two distinct usage modes. It also gives a concrete example of domestic flight exploration. This goes beyond a simple restatement, though it stops short of mentioning limitations like result size or pagination. Given the read-only nature, this level of transparency is solid.

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 moderately long but every sentence contributes useful information. It opens with the core purpose, then describes outputs, then usage modes, then filters, and closes with a practical domestic example. There is no filler or redundancy; it is well-structured and earn its length, though a few sentences could be tightened without loss.

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 tool with 20 parameters, no output schema, and no annotations, the description provides a strong contextual overlay. It covers return values, flexible vs. specific date usage, filters, and a niche use case. It doesn't explicitly explain all 20 parameters, but the schema handles that. The description is sufficient for an agent to understand when and how to use the tool, especially given the sibling context. It could mention edge cases (e.g., parameter precedence), but this is not a major 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?

Although schema coverage is 100% (baseline 3), the description adds meaningful parameter semantics beyond the schema. It explains parameter combinations: 'Use month + travel_duration for flexible date search, or outbound_date + return_date for specific dates' and gives filter guidance: 'Filter by interest (beaches, skiing, history, etc.) or region using arrival_area_id.' It also provides a concrete example for arrival_id (AEP) to clarify domestic usage. This adds context not present in the 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 clearly states the tool's function: 'Discover flight destinations and prices from a departure airport using Google Travel Explore.' It uses a specific verb (discover) with a clear resource (destinations/prices) and provides concrete examples like 'Where can I fly from London in June?' This distinguishes it from siblings such as search_flights, which would focus on specific flight searches, and it explicitly mentions open-ended holiday planning, making the purpose unmistakable.

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 gives clear guidance on when to use the tool: 'Ideal for open-ended holiday planning' with examples of queries. It also differentiates between flexible date search (month + travel_duration) and specific dates (outbound_date + return_date), and highlights a special use case for domestic flights. While it doesn't explicitly name alternatives or say 'when not to use,' the context strongly implies the tool is for exploratory discovery rather than specific flight booking, and the sibling list provides natural alternatives.

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