extract_sketch_to_gis

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

With no annotations provided, the description carries the full behavioral burden, and it does so effectively: it explicitly flags the mutation in caps ('APPENDS rows — requires confirm=true') and discloses the worker-environment prerequisite (opencv-python-headless, numpy). It does not describe failure modes (e.g., homography alignment failure) or postconditions, which keeps it from a 5.

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 dense sentences with zero filler: pipeline overview first, then the critical mutation constraint, then the environment requirement. The ALL-CAPS 'APPENDS rows' draws attention to the most safety-critical fact, and every sentence earns its place.

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 complex 12-parameter CV+GIS mutation tool with no annotations, the description covers the decisive operational facts: pipeline behavior, mandatory confirm flag, and environment prerequisites, while the schema's $defs description adds path-discipline context. It omits failure scenarios and postconditions, though an output schema exists, so a 4 is appropriate.

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?

At the reported 0% schema description coverage, the narrative must compensate, and it partially does: ink_color maps to 'requested ink color (HSV segmentation)', feature_type to 'Polygon/Polyline features', the layout envelope to the four extent parameters, and confirm to the append guard. The tuning parameters (min_contour_area_px, simplify_epsilon_px) are only recoverable from the schema's own property descriptions, so compensation is incomplete.

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 and resource ('Sketch-to-GIS pipeline') and enumerates the full workflow: homography alignment, HSV ink segmentation, georeferencing via layout envelope, and appending Polygon/Polyline features into an existing GDB feature class. This makes it unmistakably distinct from sibling ingestion/append tools like import_from_geojson, append_features, or raster_to_polygon.

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 exact trigger scenario is explicit — a smartphone photo of a hand-drawn sketch on a printed map layout that must be georeferenced and appended to a GDB. However, it never names alternatives or states when-not-to-use relative to the large sibling set that also appends or ingests features, so the differentiation is left mostly to inference.

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