Official Python SDK for Zero Context Protocol (ZCP), with MCP-compatible server surfaces and native protocol support
Critical gaps across all dimensions. Tool definitions lack proper structure: 4 duplicate weather.get_current entries (tools 1-4) suggest incomplete or malformed tool registration. Input schemas are present but inconsistent, tools 1-4 use proper JSON Schema with type/enum/required, while tools 5-8 use bare property objects without 'type' wrappers or 'required' arrays. Descriptions are minimal (10-30 chars), below the 50-200 char baseline for LLM optimization. No parameter descriptions provided for any tool. No output schemas documented. No error handling guidance. Tool naming is acceptable (verb_noun pattern) but parameter naming lacks clarity (e.g., 'unit' vs 'temperature_unit'). No evidence of tool annotations, permission gates, or audit trails.
Average a list of numbers.
Convert Celsius to Fahrenheit.
Get the current weather for one city.
Subtract b from a.
Get the current weather for a city.
Get the current weather for a city.
Get the current weather for a city.
Get the current weather for a city.
Duplicate tool definitions: weather.get_current appears 4 times (tools 1-4) with identical schemas. Indicates malformed tool registration or incomplete deduplication.
Input schemas lack proper JSON Schema structure. Tools 5-8 use bare property objects (e.g., {"city":{"type":"string"}}) instead of wrapped schemas with 'type:object', 'properties', 'required' arrays. This violates JSON Schema spec and breaks schema validation.
No parameter descriptions. All 8 tools lack descriptions for input parameters (e.g., 'city', 'unit', 'a', 'b', 'values', 'celsius'). LLMs cannot infer parameter meaning from names alone.
Tool descriptions are too brief (10-30 chars, below 50-char minimum). Examples: 'Get the current weather for a city.' (34 chars) lacks context on when to use it vs alternatives, what it returns, or prerequisites.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | 2025-06-18+ | v2 |
No output schemas documented. Tools return unspecified results. LLMs cannot plan downstream calls or extract required fields without knowing response structure.