Server has 5 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-50 chars, mostly short), and input schemas are present with Zod validation. However, descriptions lack depth, they don't explain WHEN to use each tool, dependencies, or error recovery. Parameter descriptions are minimal (e.g., 'Page number to fetch' for fetch_posts). Output schemas are not documented; responses are JSON-stringified text blobs without field-level guidance. Error handling is generic ('Error fetching posts') with no recovery hints. No tool annotations (readOnlyHint/destructiveHint) despite clear read/write distinction. Naming is verb-first and clear (fetch_*, create_*), which is good. Overall, definitions are functional but lack the depth and structure expected for agent reasoning.
Creates a new category in wordpress
Creates a new posts in wordpress
Fetches all categories from a wordpress blog
Fetches all media from wodpress blog
Fetch posts from wordpress blog
Output schemas not documented. Tools return JSON-stringified text without field-level guidance. LLMs cannot plan downstream calls or extract structured data reliably.
Descriptions are too short (10-50 chars) and lack context. They do not explain WHEN to use each tool, dependencies, or what the LLM should expect. Baseline for A+ tools is 50-200 chars with actionable guidance.
Error handling is generic and non-actionable. Errors like 'Error fetching posts' do not tell the LLM what to do next, whether to retry, or how to recover.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint/destructiveHint). create_post and create_category are write operations but lack destructiveHint. fetch_* tools lack readOnlyHint. Agents cannot distinguish safe from risky calls.
Parameter descriptions are minimal. 'Page number to fetch' and 'Number of posts per page' lack constraints (min/max). 'Array of category IDs' does not explain valid ID ranges or how to discover them.