scanProbe the terrain: ground height, solid/air, and the nearest forward obstacle. Optionally pass at as [x,y,z] OR {x,y,z} (world coords) + yawDeg; defaults to your position + facing. Use it to check "is this spot on the ground / buildable?" before building.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | World [x,y,z] or {x,y,z}, OR integer grid {gx,gy,gz} (from you.grid), to probe. Default: your position. | |
| space | Yes | ||
| yawDeg | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / additionalPropertiesAdded value: +falseInput schema / properties / at / anyOfPrevious value: -[
- {
- "properties": {
- "gx": {
- "maximum": 9007199254740991,
- "minimum": -9007199254740991,
- "type": "integer"
- },
- "gy": {
- "maximum": 9007199254740991,
- "minimum": -9007199254740991,
- "type": "integer"
- },
- "gz": {
- "maximum": 9007199254740991,
- "minimum": -9007199254740991,
- "type": "integer"
- }
- },
- "required": [
- "gx",
- "gy",
- "gz"
- ],
- "type": "object"
- },
- {
- "items": [
- {
- "type": "number"
- },
- {
- "type": "number"
- },
- {
- "type": "number"
- }
- ],
- "type": "array"
- },
- {
- "properties": {
- "x": {
- "type": "number"
- },
- "y": {
- "type": "number"
- },
- "z": {
- "type": "number"
- }
- },
- "required": [
- "x",
- "y",
- "z"
- ],
- "type": "object"
- }
-]New value: +[
+ {
+ "additionalProperties": false,
+ "properties": {
+ "gx": {
+ "type": "integer"
+ },
+ "gy": {
+ "type": "integer"
+ },
+ "gz": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "gx",
+ "gy",
+ "gz"
+ ],
+ "type": "object"
+ },
+ {
+ "items": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "number"
+ }
+ ],
+ "maxItems": 3,
+ "minItems": 3,
+ "type": "array"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "x": {
+ "type": "number"
+ },
+ "y": {
+ "type": "number"
+ },
+ "z": {
+ "type": "number"
+ }
+ },
+ "required": [
+ "x",
+ "y",
+ "z"
+ ],
+ "type": "object"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds behavioral context: probing is non-destructive, defaults to user's position and facing, and returns specific obstacle info. No contradictions; adds value beyond annotations.
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?
Two sentences: first states the action and outputs, second provides parameter guidance and usage. Front-loaded with key information, no filler, every word 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?
Covers purpose, usage, parameters, and default behavior. With no output schema, the description implies return fields (ground height, solid/air, obstacle) but does not state the return structure explicitly. Adequate for the tool's 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 description explains the 'at' and 'yawDeg' parameters with format and defaults, compensating for low schema coverage (33%). However, the required 'space' parameter is not explained at all, leaving an important gap.
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?
Description uses specific verb 'probe' with clear resource 'terrain' and explicitly lists what it returns: ground height, solid/air status, and nearest forward obstacle. This distinguishes it from sibling tools like 'look_around' or 'survey_site' by focusing on ground-level assessment.
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?
Explicitly says 'Use it to check "is this spot on the ground / buildable?" before building', providing clear when-to-use guidance. It also explains optional parameters and defaults. Lacks explicit exclusions or alternatives, but context is strong.
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.
Most tools have clearly distinct purposes, with detailed descriptions differentiating them. However, the high count (60) introduces some overlap among memory-related tools (e.g., recall_nearby_memories, search_memories, recent_memory) and environment inspection tools (look_around, look_at, survey_site), causing minor ambiguity.
The majority of tools follow a consistent verb_noun pattern (e.g., enter_space, create_commitment, recall_nearby_memories). A few names break pattern, like cognitive_boot (adjective_noun) or who_is_here (phrase), but overall the naming is predictable and readable.
With 60 tools, the server exceeds the high end of the typical well-scoped range (3-15). While the domain is complex, many tools could be consolidated (e.g., multiple memory retrieval and building tools), making the surface feel bloated rather than lean and focused.
The tool set covers the core functionalities of the 3D world—spatial navigation, building, memory, commitments, skills, and social interaction—with few obvious gaps (e.g., no direct region deletion or agent interaction beyond chat). The breadth is appropriate for the domain, though some redundancy suggests minor over-engineering.