Two tools with basic schemas and descriptions, but significant gaps in parameter documentation, output schema clarity, and error handling guidance. Tool names follow verb_noun convention (get-, list-) which is good. However, parameter descriptions lack detail on constraints, formats, and dependencies. Output schemas are not formally documented. Error responses are generic text without recovery guidance. No tool annotations (readOnlyHint, etc.). Descriptions are adequate (100-150 chars) but could be more specific about when to use each tool and what to expect.
Get the YAML definition of a schema by name and project
List all available projects (folders) in behavio-api-docs
Output schemas not documented. Tools return unstructured text responses without formal schema definitions. LLMs cannot plan downstream calls or extract structured data reliably.
Parameter descriptions lack constraint details. 'schema' param has no guidance on valid naming conventions, length limits, or case sensitivity. 'project' param default is hardcoded but not explained in description.
Error responses are generic text without recovery guidance. When schema not found or GitHub token missing, responses do not suggest next steps (e.g., 'Try list-projects first' or 'Set GITHUB_TOKEN env var').
list-projects tool has empty input schema ({}). While technically valid, the description does not explain what the tool returns or when to call it relative to get-schema-info.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Both tools are read-only and idempotent, but this is not declared in the tool registration, forcing LLMs to infer safety properties.