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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds context about the underlying Mapbox data, supported profiles (driving, walking, cycling), and returned elements (alternatives, banner/voice instructions), all consistent with annotations.

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?

Two concise, information-dense sentences cover trigger examples, core functionality, return types, profiles, and data source. There is no fluff or redundancy; every clause adds value.

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 output schema enriches return expectations and annotations cover safety, the description is largely adequate for selecting and invoking the tool. Some optional parameters are not explained, but the core invocation (coordinates, profile) is clear, and the examples in the schema provide additional usage patterns.

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?

With 0% schema description coverage, the description partially compensates by explaining coordinates, profile, alternatives, and voice/banner instructions. However, parameters like steps, overview, geometries, annotations, and language remain undocumented in both schema and description, leaving gaps.

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 explicitly states 'turn-by-turn routing between two or more coordinates' and lists concrete output types (geometry, distance, duration, voice/banner instructions). It opens with natural-language trigger examples that clearly define the tool's purpose and distinguish it from the sibling directions_matrix.

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 when-to-use signals through example queries ('Directions from A to B', 'how long does it take to drive from X to Y'). It does not explicitly exclude alternatives like directions_matrix, but the context strongly implies this is the tool for point-to-point routing.

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