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

With zero annotations, the description carries the full burden and delivers thoroughly: it discloses the per-entity-type conversion matrix, tessellation behavior, TEXT/MTEXT→point mapping with a `text` property, block INSERT expansion semantics, and the edge-case policy that 3D solids/meshes are "skipped, not errored on." It even documents the guaranteed properties.layer mapping to DXF group code 8.

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 purpose is front-loaded, followed by intent examples, then behavioral detail, then parameter guidance — a logical order. It is long, but every section earns its place given the entity-type complexity; the four example queries could be trimmed slightly without loss.

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 high-complexity format converter with no annotations, the description is remarkably complete: input behavior, output property semantics, edge-case handling, and parameter filtering are all covered, and an output schema exists to carry return-structure details. Only niche concerns like CRS/unit handling are absent, which is acceptable since DXF files inherently lack CRS metadata.

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%, so the description must compensate. The `layer` parameter is fully explained — "Pass `layer` to return only that layer's entities" — and the dxf parameter is inferable as the file's content string. Only the dxf parameter's format (raw content vs. path) is implied rather than stated outright.

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 opens with a specific verb-resource pair — "Convert an AutoCAD DXF file's contents to GeoJSON" — and enumerates concrete example phrasings an agent would match against. It is clearly distinguishable from siblings like geojson_to_dxf (reverse direction), csv_to_geojson/gpx_to_geojson (different source formats), and georeference_dxf (different operation).

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?

Multiple real-world usage examples anchor when this tool applies, including the layer-extraction case, and the description explicitly points to the companion sibling: "see list_dxf_layers to discover what layer names exist first." It stops short of explicit exclusions versus alternatives like georeference_dxf or other format converters, so the guidance is clear but not fully contrastive.

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