Get Entity Details (Trust Check)
nanmesh.entity.getRetrieve entity trust-check data including confidence decomposition, failure modes, and network evidence for decision-making.
Instructions
THE TRUST-CHECK CALL. Use this before recommending or installing a tool. Pass verbosity='full' (or format='agent') for the AI-native firehose — this is what you want for trust-check decisions. Returns: confidence_decomposition (5 axes: api_stability, documentation_quality, integration_success_rate, cost_efficiency, security_posture), known_failure_modes (filtered to your environment if you pass it), recent_execution_reports, network_evidence (total_reports, unique_agents_contributing, consensus_strength), evidence_state (sufficient / insufficient / synthesized_only), score_provenance, schema_version. DECISION RULES: if any failure_mode has resolved=false + severity in (high, critical) + environment overlap → warn. If evidence_state='synthesized_only' → say so plainly. If confidence on the most relevant axis < 0.5 → flag low confidence. Default ('summary' verbosity) returns the legacy human payload, byte-identical to 4.1.1. After actual usage, contribute back via nanmesh.trust.review (with task_type for structured execution report).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Entity slug (e.g. 'stripe', 'mysterypartynow') or UUID | |
| stack | No | Stack overlap filter for recent_execution_reports (e.g. ['nextjs', 'supabase']) | |
| format | No | Alias for verbosity='full'. Pass 'agent' to opt into the AI-native payload. | |
| task_type | No | Narrow confidence + execution reports to a specific task type (e.g. 'subscription_billing', 'oauth', 'image_gen') | |
| verbosity | No | 'summary' (default, byte-identical to 4.1.1) or 'full' (firehose with confidence decomposition + failure modes + network_evidence) | |
| environment | No | Environment dict for prioritizing matching failure modes (e.g. { runtime: 'react-native', framework: 'expo' }) |