@kind-ling/twig

Analyzes tool definitions and their descriptions through LLM inference to identify clarity, completeness, and discoverability gaps that prevent agent selection. Uses prompt engineering to evaluate descriptions against agent decision-making criteria, generating structured feedback on how to improve tool adoption by AI agents. The optimizer examines parameter documentation, use-case clarity, and schema expressiveness to surface optimization opportunities.

Parses and validates MCP tool schema definitions to identify missing or ambiguous parameter documentation, incomplete type specifications, and unclear use-case descriptions that reduce agent selection probability. Performs structural analysis of JSON schemas to detect gaps in required fields, examples, and constraint definitions that agents rely on for tool understanding.

Generates improved tool descriptions optimized for LLM agent comprehension by reframing existing descriptions to emphasize use-case clarity, parameter necessity, and invocation patterns that agents prioritize. Uses prompt engineering to produce descriptions that highlight when and why an agent should select this tool, incorporating agent decision-making heuristics into the generated text.

Calculates quantitative scores for tool descriptions based on agent-selection factors including clarity, specificity, use-case coverage, and parameter documentation completeness. Provides numeric ratings that help developers understand relative tool quality and track improvements over time, using weighted scoring criteria derived from agent decision-making patterns.

Processes multiple MCP tool definitions in a single operation, analyzing them collectively to identify patterns, inconsistencies, and relative quality gaps across a tool ecosystem. Enables comparative analysis where tools are evaluated not just individually but in context of other available tools, helping agents understand differentiation and selection criteria.