Loading ToolBench
MCP server for Anime News Network. Search the anime and manga encyclopedia, read cast, staff and episodes, and follow the news wire. No API key required.
Server has 4 tools with complete input schemas and descriptions. Tool names follow verb_noun convention (search_, get_, list_). Descriptions are present but brief (10-50 chars), below the 50-200 char LLM-optimized baseline. Parameters have types and descriptions, but lack constraints (enums, ranges, format specs). No output schemas documented. Error handling not visible in provided code. All tools are READ_ONLY, reducing risk but also limiting composition complexity.
Read the news wire
Read an encyclopedia entry
List recent or browse alphabetically
Search the encyclopedia
Descriptions are too brief (10-50 chars). LLM-optimized descriptions should be 50-200 chars, explaining WHAT the tool does, WHEN to use it, and any prerequisites. Current descriptions lack context for tool selection.
No output schemas documented. LLMs need to know what fields to expect in responses to plan downstream calls and extract data correctly. Responses should be structured with typed fields.
Parameters lack constraints. 'kind' should be an enum (anime|manga), 'limit' and 'offset' need min/max bounds, 'sections' should enumerate valid options. Free-form strings invite hallucinated values.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2025-06-18+ | v2 |
No error handling guidance visible. Error responses should tell LLMs what to do next (retry, ask user, or fail). Raw errors or stack traces give agents nothing to act on.
list_recent lacks pagination documentation. Tools returning lists should accept limit/offset and return total count or next_cursor. Without pagination guidance, large results risk context window exhaustion.