predictionguard

pg_whale_alerts

Retrieve alerts from the watchlist audit log. Filter by address, severity (LOW/MEDIUM/HIGH/CRITICAL), and/or ISO timestamp 'since'. Default returns the 50 most recent alerts across the whole watchlist.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pg_whale_alerts"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max results (max 500)
`since`	No	ISO 8601 timestamp (e.g. 2026-04-20T00:00:00Z)
`address`	No
`severity`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedMay 7, 2026

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden of disclosing behavior. It does mention the default limit of 50 and the cross-watchlist scope, which is useful. However, it does not disclose potential side effects, rate limits, or other edge cases, though the read-only nature is implied by 'retrieve'.

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 two sentences long, front-loaded with the core purpose, and includes all essential information without redundancy. Every clause adds value, from the resource type to the filter options and default behavior.

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?

For a simple retrieval tool with no required parameters and no output schema, the description provides sufficient context: the source (watchlist audit log), filtering options, and default limit. It does not detail the return structure, but given the simplicity, it is adequately complete.

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?

The schema has descriptions for only half of the parameters (limit and since). The description adds meaning to the undocumented 'address' and 'severity' parameters by explaining they are filters, and explicitly lists severity values. It also clarifies that 'since' is an ISO timestamp, augmenting the schema information.

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 the tool retrieves alerts from the watchlist audit log, using the specific verb 'Retrieve' and a defined resource. It also distinguishes itself from sibling tools like pg_whale_list by focusing on the audit log alerts rather than watchlist management.

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

Usage Guidelines3/5

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

The description explains that it can be filtered by address, severity, and since, and notes the default behavior of returning the 50 most recent alerts. However, it does not explicitly mention when to use this tool over alternatives or when not to use it, leaving some ambiguity regarding its place among sibling tools.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?