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

The description adds valuable behavioral context by specifying that it 'Returns the file contents,' which informs the agent how the output will be consumed, a detail not covered by the readOnlyHint annotation. This clarifies the nature of the output as data rather than a URL to a file.

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 concise and highly efficient, using two clauses to explain the input flexibility (link OR list of stops) and the resulting output formats (CSV or KML). No sentence is wasted.

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?

The description provides all necessary contextual information for the tool to be used correctly, including the nature of the inputs and the functional utility of the outputs. Since there is no output schema, the description successfully addresses the result of the call.

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?

Despite 33% schema description coverage gap, the description provides rich semantic meaning for the 'format' enum parameter by explaining the functional utility of both CSV (Google My Maps import) and KML (Google Earth, My Maps). This adds critical context beyond just listing the allowed strings.

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 core purpose: converting inputs (maps link or list of stops) into structured file formats (CSV/KML). It distinguishes itself by the 'export' action and the specific output formats, which differentiates it from sibling tools like 'geocode' or 'parse_map_link'.

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 implies usage when the user requires a transferable file format (CSV/KML), but it doesn't explicitly state whether to use this tool before or after another sibling tool like 'parse_map_link'. The guidance is sufficient but not prescriptive.

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