Import CSV rows as point entities in CAD drawings for sampling points or monitoring wells, preserving tabular attributes.
Import CSV rows into point entities for sampling points or monitoring wells while preserving tabular attributes.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| path | No | ||
| unit | No | ||
| layer | No | ||
| content | No | ||
| encoding | No | ||
| x_column | No | ||
| y_column | No | ||
| z_column | No | ||
| id_column | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'Import' implies creation of entities, but it never says whether existing points are merged or duplicated, what permissions are needed, how source vs destination CRS are handled via the unit parameter, or what happens on malformed rows. Only 'preserving tabular attributes' adds any behavioral signal.
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?
A single front-loaded sentence with no filler; verb, resource, target domains, and the attribute-preservation property come in order. It is short, though the brevity is partly under-specification rather than discipline.
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 10-parameter mutation tool with zero annotation coverage and no output schema, the description is far too thin. It omits the file/encoding duality, coordinate-column mapping, units, and the layer target, all of which the agent must know to call this correctly.
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% across 10 parameters, so the description must compensate and largely does not. It alludes to attribute columns ('preserving tabular attributes') but never explains kind, path vs content vs encoding, unit, layer, or the x/y/z/id column mappings, which are the parameters an agent most likely gets wrong.
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?
States a specific verb (import) and resource (CSV rows into point entities) with the domain scope (sampling points or monitoring wells) and a key property (tabular attributes preserved). It is clearly distinguishable from the CAD import siblings (import_step, import_dxf), though it never names create_point or create_sampling_point as the non-CSV alternative.
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 names the target entity kinds but gives no when-to-use guidance, no prerequisites (must the layer exist? must CRS be set?), and no comparison against siblings like create_sampling_point or import_geojson. The agent must infer usage entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.