A Model Context Protocol server to generate API clients by using TypeScript.
Single tool with complete input schema and clear naming. Tool name 'generate_client' follows verb_noun convention and is unambiguous. Input schema is well-formed with 3 required parameters, all typed and described. However, output schema is not documented, LLMs cannot predict the response structure. Error handling returns text responses but lacks actionable recovery guidance. No parameter constraints beyond enum for httpClient. Tool description is adequate (89 chars) but could better explain when to use it vs alternatives or what prerequisites exist.
Generate TypeScript API client from OpenAPI specification
Output schema not documented. LLMs cannot predict response structure (success vs error, fields returned, file list format). Agents cannot plan downstream operations.
Error responses lack actionable recovery guidance. Returns raw error messages but does not tell LLM what to do next (retry, ask user, check input format). Violates recovery-guide pattern.
Input parameter 'input' accepts both URL and file path but lacks format constraints. Description says 'URL or file path' but no regex, examples, or validation rules. LLMs may pass invalid paths.
Output directory parameter has no validation constraints. No mention of required permissions, max path length, or behavior if directory already contains files (overwrite vs error). Ambiguous for LLM.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Tool description does not state that this operation modifies filesystem state (creates files). Agents need to know which calls are safe to retry and which have side effects.