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

With no annotations, the description carries the burden and provides key behavioral details: per-feature processing, property preservation ('Properties are kept'), and return format ('Returns JSON {ok, geojson}'). It omits error handling, but for a pure read-only computation this is acceptable.

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 short, impactful sentences: action with definition and examples, property preservation, and return shape. Every clause earns its place with no filler.

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 per-feature bounding-box utility, the description covers the core behavior, provides examples, notes property preservation, and states the JSON response. An output schema exists so detailed return fields are not necessary. The only minor gap is explicit input format guidance, but the parameter name and examples make it discoverable.

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 0%, and the description never explains the geojson parameter beyond the schema's type string. There is no guidance on expected GeoJSON structure, coordinate order, or constraints, so it fails to compensate for the low schema coverage.

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 the bounding box (min/max rectangle) around each feature' with a specific verb and resource, and provides natural-language examples. It distinguishes itself from geometric siblings like convex_hull_geojson and minimum_rotated_rectangle by emphasizing per-feature rectangular extent.

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 includes example user phrasings such as 'get the bounding box of this shape' and 'bbox for each feature', which signal when to use the tool. However, it does not explicitly exclude alternatives like convex hull or minimum rotated rectangle, so it stops short of full guidance.

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