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

With no annotations provided, the description carries the full burden of disclosing behavior. It names the algorithm (Douglas-Peucker), explains the tolerance parameter's effect ('lower = more detail kept'), and notes tolerance is in degrees. This is useful behavioral context beyond what the schema provides. However, it does not explicitly state that the tool returns a new geometry without mutating the input, though this is implicitly understood from typical transformation tools.

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 two sentences, with the core purpose in the first sentence and supporting examples and tolerance details in the second. It is front-loaded, uses no filler words, and every clause carries meaningful information. The structure is ideal for quick parsing by an AI agent.

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 simple transformation tool, the description covers the essential aspects: what it does, how the tolerance works, and example use cases. An output schema exists, so the return value is documented elsewhere. The description could be slightly more complete by mentioning that the input is not modified or by specifying the output format, but given the output schema, this is not a major concern. Overall, it is sufficiently complete for its complexity.

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?

The schema has zero description coverage for parameters, so the description must compensate. It explicitly explains the tolerance parameter ('Tolerance in degrees; lower = more detail kept'), which adds significant meaning beyond the schema's bare number type. The geojson parameter is implied by the tool name and description ('GeoJSON geometry'), but the description does not explicitly specify the expected format (e.g., a GeoJSON string). This is a minor gap.

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 purpose: 'Reduce the number of vertices in GeoJSON geometry' using the Douglas-Peucker algorithm. It includes concrete example inputs ('simplify this polygon', 'this shape has too many points') that reinforce the intended use, and the verb+resource combination distinguishes it from sibling geometry tools like buffer_geojson or centroids_geojson.

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 contextual use cases ('reduce vertex count for faster rendering') and example commands that indicate when a user would need this tool. It does not explicitly mention alternatives or when not to use it, but the examples effectively convey the common scenarios. A slight deduction for not naming alternative tools or exclusion criteria.

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