Skip to main content
Glama

Get Fraud Metrics

paybond_get_fraud_metrics
Read-only

Retrieves tenant-wide Signal fraud backtesting and monitoring metrics over a rolling window, including flagged operators, severity counts, review outcomes, precision, false-positive rates, and backtest summary.

Instructions

Use this when you need tenant-wide Signal fraud backtesting and monitoring metrics over a rolling window (flagged operators, severity counts, review outcomes, precision/false-positive rates, and backtest_summary). Requires PAYBOND_API_KEY with Signal analytics read access and the private-dashboards feature. Do not use this for one operator's fraud posture—call paybond_get_fraud_assessment instead—or for Harbor intent escrow detail—call paybond_get_intent. Idempotent read with no side effects; omit window to default to 24h; unsupported windows fail with HTTP 400 ("window must be one of 24h, 7d, or 30d").

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
windowNoRolling metrics window. Allowed values: 24h, 7d, 30d. Omit to use the gateway default 24h. Unsupported values fail with HTTP 400.
score_versionNoOptional Signal score model version to query. Omit to use the gateway default current model (1.0). Example: 1.0.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
windowNoActive metrics window label: 24h, 7d, or 30d.
tenant_idNoTenant echoed by the gateway for the authenticated API key (example: tenant-a).
window_ended_atNoRFC3339 end of the evaluated rolling window.
backtest_summaryNoHuman-readable backtest summary derived from the window metrics.
high_signal_countNoCount of high-severity fraud signals in the window.
review_open_countNoOperators currently in an open review state.
window_started_atNoRFC3339 start of the evaluated rolling window.
score_model_versionNoScore model version used for the metrics (echoes the requested score_version or the gateway default 1.0).
confirmed_risk_countNoLabeled confirmed-risk outcomes in the window.
false_positive_countNoLabeled false-positive outcomes in the window.
critical_signal_countNoCount of critical-severity fraud signals in the window.
elevated_signal_countNoCount of elevated-severity fraud signals in the window.
labeled_outcome_countNoReview outcomes labeled in the window (confirmed risk, false positive, or needs more evidence).
flagged_operator_countNoOperators with at least one fraud signal in the window.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds that it is an idempotent read with no side effects, and specifies error behavior (HTTP 400 for unsupported windows). This adds useful context beyond annotations, though the core behavioral traits are already covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with multiple sentences each serving a purpose: stating usage, listing alternatives, providing requirements, and explaining parameter behavior. No fluff, though slightly dense; still effective and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given only 2 non-required parameters with full schema coverage, annotations present, and output schema exists, the description covers purpose, usage, behavioral details, error conditions, and all parameter semantics. It is complete for a read-only metrics tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (both parameters described in schema). The description adds value by clarifying that omitting window defaults to 24h and unsupported values fail with HTTP 400, and that omitting score_version defaults to current model (1.0). This enriches the semantic understanding beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves tenant-wide fraud metrics over a rolling window, and distinguishes from sibling tools by explicitly saying not to use for single operator (paybond_get_fraud_assessment) or intent details (paybond_get_intent), and not for Harbor intent escrow. The verb 'get' is specific to the resource 'fraud metrics' with explicit scope 'tenant-wide'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool (for tenant-wide metrics) and when not to (for one operator or intent escrow), naming the correct alternative tools. It also provides requirements (PAYBOND_API_KEY, private-dashboards feature) and default/error behavior for parameters, giving clear guidance for agent invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nonameuserd/paybond-kit-python'

If you have feedback or need assistance with the MCP directory API, please join our Discord server