Loading ToolBench
Exposes value-leak discovery (melt_analyze_value_vectors, melt_estimate_annual_leak) and a lead-capture handoff (melt_request_scan) to Claude, Cursor, GitHub Copilot, and any MCP-compatible agent.
Three tools with complete schemas, strong descriptions (194 - 380 chars), and clear enum constraints. Naming follows verb_noun pattern (analyze_, estimate_, request_). All parameters typed and described. Output schemas documented in descriptions. Error handling present but recovery guidance minimal. Tool composition is sound, each does one thing. Main gaps: no tool annotations (readOnlyHint/destructiveHint), descriptions could be more concise for LLM parsing, and error messages lack actionable recovery steps.
Estimates where AI/software value is most likely leaking out of a single department, based on headcount, labor cost, and the type of chaotic/unstructured input it processes manually today. Use this when a tech leader asks where value is being lost or where AI would create the most immediate impact in their org, before any real data integration exists — this is Melt's free Stage-1 Sandbox estimate. Output is directional, from synthetic/self-reported inputs, not an audited figure — for a real finding tied to an actual system log, follow up with melt_request_scan. Also answers what earlier Melt materials called 'AI ROI leverage' or 'AI value vectors' — same estimate, older name.
Quantifies a specific, already-identified value-leak pattern in dollars per year — e.g. reps bypassing a coaching tool's summaries, manual overrides corrupting a forecasting model, a manual handoff between two systems. Use this when a leak pattern and its rough volume/rate are already known or hypothesized. This mirrors Melt's real scan methodology (see the fintech case study: a 29% Gong bypass rate, a 62% Clari override rate, and a 4.2-day manual handoff combined into a $77,235/yr finding) — it is a directional estimate from self-reported numbers, not a scan against real system logs. For an audited figure, follow up with melt_request_scan. Covers what earlier Melt materials called 'Feature Waste Dollar Amount' (money leaking on licensed-but-unused software) and general 'AI ROI leverage' calculations — those are older names for this same value-leak math, not a different tool.
Submits a request for a Melt scan — the next step after Melt's free Stage-1 Sandbox estimate, moving to a real, log-verified value-leak finding tied to a dollar figure and a source system. Call this only after the user has explicitly asked to be connected with Melt or to book/request a scan — never submit contact details the user hasn't provided themselves. Earlier Melt materials called this a 'Thermal Scan' — same request, current name is just 'a scan' (no fixed 2-week/pricing claim attached anymore).
Tool annotations missing: no readOnlyHint, destructiveHint, or idempotentHint declared. melt_request_scan is marked WRITE in comments but not via schema annotations.
Error handling lacks recovery guidance. No examples of error responses or actionable next steps for LLM (e.g., 'If validation fails, check that departmentType is one of: Operations, Finance, ...').
Tool descriptions are verbose (194 - 380 chars, baseline p90=392). melt_analyze_value_vectors and melt_estimate_annual_leak include lengthy disclaimers about synthetic data and earlier naming conventions, diluting the core action. Trim to 100 - 150 chars for faster LLM parsing.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 67 | 2026-07-28+ | v2 |
melt_request_scan parameters (company, contactEmail, contactName, departmentsOfInterest, notes) are all optional. No guidance on which are required for a valid scan request or what happens if all are omitted.
Output schemas not formally documented in code. Descriptions mention 'Output is directional' and 'returns' but no explicit JSON schema for response structure (e.g., what fields does melt_analyze_value_vectors return?).