添加 GeoJSON 图层到地图（支持 Point/Line/Polygon，可配置颜色/分级/分类渲染）
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | 图层ID（不传则自动生成） | |
| data | Yes | GeoJSON FeatureCollection 对象 | |
| name | No | 图层显示名称 | |
| style | No | 样式配置（color, opacity, pointSize, choropleth, category） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all false, providing no meaningful safety flags. The description adds supported types and rendering modes but does not disclose side effects such as behavior when an existing 'id' is reused or whether the operation is idempotent. No contradiction with annotations, but the description does not carry the full behavioral burden.
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 description is a single, concise sentence that front-loads the primary action and key capabilities. Every phrase adds value, with no wasted words 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?
For a tool with four parameters, one nested style object, and no output schema, the description provides a solid overview of purpose and key options. The schema covers parameter details well, but the description does not mention return values or potential side effects, leaving slight incompleteness.
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 descriptions cover all four parameters (100% coverage), so the baseline is 3. The description's mention of graduated/categorical rendering aligns with the 'style' parameter's 'choropleth' and 'category' properties, adding marginal context. However, it does not explain individual parameters beyond what the schema already provides.
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 the action ('Add GeoJSON layer to map') and specifies supported geometry types (Point/Line/Polygon) and configurable rendering (color/graduated/categorical). This differentiates it from sibling tools like addPolygon or addPolyline, which likely handle single geometric primitives rather than full GeoJSON layers.
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 usage when the user needs to add a GeoJSON layer, but it does not explicitly compare with alternatives or state when not to use this tool. No alternative tools are named, so the guidance is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools share conceptual boundaries (e.g., addMarker vs addBillboard vs addLabel, addPolyline vs addCorridor vs addWall, flyTo vs setView), though descriptions clarify most cases. The overlap is notable given the large tool count.
All tools use lowerCamelCase with a consistent verb-first pattern (add*, load*, set*, remove*, update*). Some generic verbs like control and update are reused, but the naming is predictable and readable.
43 tools is well beyond the recommended range. Many add* functions for different primitive types could be consolidated into one entity-creation tool, reducing bloat and cognitive load without sacrificing capability.
The tool set offers strong coverage across entities, layers, camera controls, and animations. Minor gaps include lack of entity information retrieval and direct geometry re-editing, but core workflows are well supported.