King native PHP extension with pipeline orchestrator, MCP tool registry, WebSocket server, HTTP client, and autoscaling capabilities
King exposes 2 tools with minimal documentation and incomplete schemas. Tool 1 (structured_mini_language) has a vague description and an array-type input with no field documentation, impossible for an LLM to construct valid payloads. Tool 2 (count_occurrences) has better parameter naming but lacks descriptions for its inputs. Neither tool documents output schemas. No error handling guidance, no parameter constraints, no examples of valid input. Descriptions are under 50 chars, violating the 10 - 1024 char baseline. No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Both tools are READ_ONLY but this is not reflected in descriptions or error handling patterns.
Count occurrences of a pattern in text
Structured mini language for inference operations
Tool 1 input schema is an undocumented array with no field descriptions. LLMs cannot construct valid payloads without knowing what array elements represent.
Both tool descriptions are under 50 characters and lack WHAT/WHEN/WHY context. Descriptions must be 10 - 1024 chars and explain when to use the tool and what it returns.
No output schemas documented. LLMs cannot plan downstream tool calls or extract results without knowing the response structure.
Tool 2 parameters 'text' and 'pattern' lack descriptions. Parameter descriptions are mandatory, LLMs cannot infer meaning from names alone.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |
No error handling guidance. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next.