Single tool 'meshprobe' has a basic description (56 chars) but critically lacks a documented input schema. The Command parameter is typed as a Pydantic model (Command union type from protocol module) but the actual schema structure is not visible in the provided source. Parameter descriptions are absent. No output schema is documented. The tool description does not explain WHEN to use it, what prerequisites exist, or what the response structure contains. Naming is generic ('meshprobe' as a tool name is the same as the server name) and does not follow verb_noun convention. No error handling guidance is provided.
Execute one typed read-only 3D inspection operation.
Input schema not visible in source code. Command parameter is typed as a Pydantic union but the actual JSON Schema structure, field names, types, and constraints are not documented or shown. Cannot verify schema completeness.
Tool name 'meshprobe' is generic and does not follow verb_noun convention. It is identical to the server name, providing no semantic hint about the action. Should be 'inspect_model', 'query_geometry', or similar action-oriented name.
Parameter 'command' lacks a description. LLMs cannot infer what types of commands are valid, what fields the Command union accepts, or when to use each variant. Description is required per pattern:tool-description.
Output schema is not documented. Tool description does not specify what CommandResponse or OperationReceipt contain, what fields are returned, or how to interpret the response. LLMs cannot plan downstream actions without knowing the response structure.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2026-07-28+ | v2 |
Tool description (56 chars) is too brief and lacks context. Does not explain WHAT inspection operations are supported, WHEN to call this tool, what prerequisites exist (e.g. must load a model first?), or what the response contains. Baseline for A+ tools is 50-200 chars with explicit WHAT/WHEN/HOW guidance.