predictionguard

pg_sar_report

Generate a draft Suspicious Activity Report (SAR/STR) from structured inputs. Supports EU_GENERIC (FATF-aligned STR, default), US_FINCEN (Form 111 structure), and DE_goAML (German FIU draft). Takes subject, market, activity window, integrity signals, and evidence references — auto-classifies the primary suspicious activity type, generates a narrative, and renders regulator-style markdown. Output is marked draft_for_review; PredictionGuard does not submit SARs directly.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`filer`	No	Information about the preparing institution.
`market`	No	Optional. Polymarket market context.
`signals`	No	Integrity signals (strings or objects with 'term'/'reason'/'layer'). Pass the 'triggered_signals' array from pg_market_integrity_scan or pg_resolution_risk_score directly.
`subject`	Yes	Required. The subject of the report.
`activity`	No	Activity window and amounts.
`evidence`	No	References to prior evidence.
`narrative_addendum`	No	Optional free-text addendum from the analyst.
`filing_jurisdiction`	No	Report format. Default EU_GENERIC.	EU_GENERIC

TDQS

A4.4/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses that the output is marked 'draft_for_review' and that 'PredictionGuard does not submit SARs directly,' which is key behavioral context. It does not mention permissions, side effects, or failure modes, but the draft/non-submission caveat is significant.

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

Conciseness5/5

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

The description is three sentences with no padding. It front-loads the core purpose, then covers supported formats, inputs, behavior, and output status efficiently. Every sentence contributes useful information.

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

Completeness4/5

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

Given the tool's complexity (8 parameters, nested objects, no output schema), the description covers the main workflow, jurisdiction options, and output format. It does not describe the exact structure of the generated markdown report or edge-case behavior, but the high schema coverage compensates for most omissions.

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%, so baseline is 3. The description adds value by explaining the filing_jurisdiction enum values ('FATF-aligned STR', 'Form 111 structure', 'German FIU draft') and by grouping the key inputs (subject, market, activity window, signals, evidence), which helps the agent understand how to populate parameters beyond the schema.

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 'Generates a draft Suspicious Activity Report (SAR/STR) from structured inputs' and names the supported jurisdictions (EU_GENERIC, US_FINCEN, DE_goAML). This specific verb+resource, combined with the output type, distinguishes it from the sibling scan/analysis tools.

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

Usage Guidelines4/5

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

The description implies downstream usage by referencing 'integrity signals' and 'evidence references' from prior tools, and it clarifies the report is a draft for review. However, it does not explicitly state when not to use this tool or name alternative tools, so it lacks full exclusionary guidance.

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

All predictionguard tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation5/5

Each tool has a clear, distinct purpose covering different aspects of prediction market integrity (market analysis, wallet analysis, AML/KYC, alerting, reporting). There is minimal overlap risk, as even related tools (e.g., pg_insider_signal_scan vs. pg_information_advantage_score) are differentiated by input (market vs. wallet) and output type.

Naming Consistency4/5

All tools share the 'pg_' prefix and use descriptive snake_case names, making the set predictable. However, the verb/noun order is inconsistent (e.g., pg_whale_add vs. pg_market_details). The pattern is still clear and functional, so minor deviation from a strict verb_noun pattern.

Tool Count4/5

With 33 tools, the set is large but well-scoped for a comprehensive platform covering market analysis, wallet intelligence, compliance, and reporting. Each tool serves a distinct function, and the count is justified by the breadth of the domain, though it pushes the upper bound of 'reasonable'.

Completeness5/5

The toolset covers the full lifecycle of prediction market integrity work: from market discovery and integrity scanning to wallet analysis, entity resolution, AML/KYC, watchlist management, alerting, and SAR reporting. There are no obvious gaps for the stated purpose.

Resources

Need Help?