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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds behavioral context by explaining the snapping process and what the output contains (matched geometry, distance, time, road names, confidence). It also frames the result as 'the road-accurate route that was actually driven,' which clarifies the nature of the operation beyond the annotations. However, it doesn't address rate limits or authorization nuances, though these are not necessarily expected given the annotations. No contradiction 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?

The description is three sentences long, each earning its place: the first defines the core action, the second describes inputs and outputs, and the third gives use cases and a cross-reference to an alternative. It is front-loaded with the main purpose and contains no fluff or redundant details.

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 tool's complexity (4 parameters, output schema, annotations), the description is remarkably complete. It covers purpose, use cases, an explicit alternative, input constraints (2–100 points), and a summary of outputs. The output schema details the full return structure, and annotations cover safety and semantics, so the description does not need to repeat those. It also implicitly differentiates from other trace-related siblings like 'trace_attributes' by focusing on map matching to a road network, though it doesn't mention that tool by name – still acceptable because the explicit 'directions' alternative is the most likely confusion point.

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 baseline is 3. The description restates the shape constraint ('2–100 points') but does not add additional meaning for 'costing', 'search_radius', or 'vehicle_profile' beyond what the schema already provides. It also doesn't explain parameter interactions (e.g., vehicle_profile implying costing=truck) that are in the schema. Thus, the description adds marginal value over 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 'Map matching snaps raw GPS breadcrumbs to the road network' with a specific verb and resource. It also distinguishes itself from the sibling 'directions' tool by explicitly noting that for route planning, one should use 'directions' instead. This makes the purpose unambiguous and well-differentiated.

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 explicit use cases: 'Use for fleet trace cleanup, mileage from GPS logs, and reconstructing routes from telemetry.' It also gives a clear exclusion: 'For planning a route between places, use `directions` instead.' This directly tells the agent when to pick this tool over an alternative, fulfilling the highest bar for usage guidance.

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