Remove a layer, field, or upload from the spatial portal by specifying its id and kind, with confirmation required to apply changes.
Delete a layer (numeric id), a field (cl…/el… id) or an upload (upload id) [changes spatial-service]
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| kind | Yes | ||
| confirm | No | Must be true (and dryRun false) to really do it |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true and readOnlyHint=false, so the agent knows this is a mutating, destructive operation. The description's '[changes spatial-service]' is a vague side-effect note that adds minimal new information beyond the annotations. It does not disclose confirmation requirements, irreversibility, or permissions, though confirm is documented in the schema.
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 entire description is one sentence, with the action and resource types front-loaded. The trailing note is compact and does not repeat schema content. No filler or redundancy.
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?
With three parameters, a destructive flag, and no output schema, the description plus annotations and schema give enough to invoke the tool: kinds and id formats are covered, confirm is documented in the schema, and destructiveness is annotated. It doesn't describe the return value, but none is specified, and the tool is a simple delete operation. Overall, it is sufficiently complete for the 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 only describes the confirm parameter (33% coverage). The description compensates by defining the expected id format for each kind: numeric ids for layers, 'cl…/el…' ids for fields, and upload ids. This is essential meaning that the raw schema does not provide, making the tool callable correctly.
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 names the verb 'Delete' and the three resource kinds (layer, field, upload) with id formats, making the tool's scope immediately clear. The explicit list distinguishes it from spatial_delete_area, which handles areas. No ambiguity remains about what the tool targets.
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 implies its use case by enumerating the deletable resource types, but it does not explicitly say when to prefer this tool over alternatives or when not to use it. It never mentions spatial_delete_area or creation/update tools, leaving the agent to infer routing from sibling names. This is adequate but lacks explicit exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.