compute_route_matrix

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

Annotations already confirm read-only, non-destructive behavior. The description adds valuable context: Google bills per pair and the matrix is capped at 100 origin-destination pairs. This exceeds what annotations provide, though it doesn't detail error behaviors or rate limits.

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?

Three sentences with no redundancy. The first sentence defines purpose, the second gives use cases, and the third adds a critical constraint. Every sentencence 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?

Covers the high-level concept, use cases, and a key constraint (100-pair cap). However, with 7 parameters and no output schema shown, it fails to specify input format details (e.g., how to represent coordinates or addresses), which is essential for correct usage.

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 0%, yet the description only mentions origins and destinations and vaguely references 'the same three forms as compute_route'. It does not explain the meaning of travel_mode, avoid options, departure_time, or how to format address strings. Relies heavily on external knowledge.

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 'Get travel time and distance for every origin against every destination in one call' and labels it 'the comparison tool'. Specific use cases like picking nearest branch or ranking sites are given, and it distinguishes itself from sibling tools like compute_route by doing all pairs in a single call.

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 provides clear usage contexts (nearest branch, ranking sites, reachability checks) and mentions the 100-pair cap. It implicitly contrasts with compute_route for single routes but does not explicitly state when not to use this tool or name alternatives.

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