Skip to main content
Glama

Detections

detections
Read-onlyIdempotent

Anomalies our detectors logged, newest first: drain-shaped payments (each with the share of the wallet's balance it took), retry storms, mint bursts, fleet-funding fan-outs (layering_fan), owner changes under a binding, delegation to unknown code. A detection is a shape with evidence, never a verdict. Filter by agent, kind, severity, time or live incidents only; compact drops the glossaries.

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": "detections"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOnly detections of this kind. own_move and sibling_withdrawn are earlier drain alerts that were read again as the wallet's own move and are kept in the log
agentNoOptional agent id (act_8453_N or token id)
limitNoHow many detections to return, 1 to 25 (default 10)
sinceNoISO time; only detections at or after it
compactNoLeave out the glossaries and tier notes
severityNoOnly detections of this severity
live_onlyNoOnly detections that are live incidents

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / kind / description
      Added value: +"Only detections of this kind. own_move and sibling_withdrawn are earlier drain alerts that were read again as the wallet's own move and are kept in the log"
    • addedInput schema / properties / limit / description
      Added value: +"How many detections to return, 1 to 25 (default 10)"
    • addedInput schema / properties / severity / description
      Added value: +"Only detections of this severity"
  2. Changed1 schema field changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "drain_pattern",
      -  "test_then_drain",
      -  "address_poisoning_loss",
      -  "approval_to_plain_key",
      -  "fleet_sibling_exposure",
      -  "retry_storm",
      -  "mint_burst",
      -  "layering_fan",
      -  "uri_timeout_streak",
      -  "bind_closed_after_nft_transfer",
      -  "delegate_changed",
      -  "god_key_unknown_7702",
      -  "reputation_farming"
      -]New value: +[
      +  "drain_pattern",
      +  "test_then_drain",
      +  "address_poisoning_loss",
      +  "approval_to_plain_key",
      +  "fleet_sibling_exposure",
      +  "retry_storm",
      +  "mint_burst",
      +  "layering_fan",
      +  "uri_timeout_streak",
      +  "bind_closed_after_nft_transfer",
      +  "delegate_changed",
      +  "god_key_unknown_7702",
      +  "reputation_farming",
      +  "own_move",
      +  "sibling_withdrawn"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "drain_pattern",
      -  "retry_storm",
      -  "mint_burst",
      -  "layering_fan",
      -  "uri_timeout_streak",
      -  "bind_closed_after_nft_transfer",
      -  "god_key_unknown_7702"
      -]New value: +[
      +  "drain_pattern",
      +  "test_then_drain",
      +  "address_poisoning_loss",
      +  "approval_to_plain_key",
      +  "fleet_sibling_exposure",
      +  "retry_storm",
      +  "mint_burst",
      +  "layering_fan",
      +  "uri_timeout_streak",
      +  "bind_closed_after_nft_transfer",
      +  "delegate_changed",
      +  "god_key_unknown_7702",
      +  "reputation_farming"
      +]
  4. Changed5 schema fields changed
    • addedInput schema / properties / compact
      Added value: +{
      +  "description": "Leave out the glossaries and tier notes",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / kind
      Added value: +{
      +  "enum": [
      +    "drain_pattern",
      +    "retry_storm",
      +    "mint_burst",
      +    "layering_fan",
      +    "uri_timeout_streak",
      +    "bind_closed_after_nft_transfer",
      +    "god_key_unknown_7702"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / live_only
      Added value: +{
      +  "description": "Only detections that are live incidents",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / severity
      Added value: +{
      +  "enum": [
      +    "info",
      +    "notable",
      +    "major"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / since
      Added value: +{
      +  "description": "ISO time; only detections at or after it",
      +  "type": "string"
      +}
  5. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely non-structured behavior: results are ordered newest first, drain detections carry the share of wallet balance taken, and 'compact' suppresses glossaries — plus the important interpretive caveat that detections are evidence, not verdicts.

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?

Front-loaded with the resource and ordering, then the kind catalog, then the interpretive caveat, then filters. Dense but nearly every clause carries information; the parenthetical kind list is long but each entry earns its place by disambiguating what 'detection' means.

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?

No output schema exists, so the description must convey return shape — it does so partially (newest-first ordering, drain entries include balance-share, glossaries present unless compact). For a read-only list tool with fully documented params this is close to sufficient; a sentence on pagination or total-count behavior would close the gap.

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

Parameters3/5

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

Schema description coverage is 100%, so all seven parameters including both enums are already documented. The description restates the filter set and the compact behavior without adding syntax or format detail beyond the schema (e.g. no 'since' format or limit guidance beyond what is written). Baseline 3 applies.

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?

States a specific verb+resource ('Anomalies our detectors logged') and immediately enumerates the concrete detection shapes covered (drain-shaped payments, retry storms, mint bursts, layering_fan, owner changes, delegation to unknown code), plus ordering ('newest first'). An agent knows exactly what corpus it is querying without opening the schema.

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?

Gives clear operating context: the filter dimensions available and the framing that 'a detection is a shape with evidence, never a verdict', which tells the agent how to interpret results rather than treat them as conclusions. It stops short of naming when to prefer a sibling like evidence_pack_quote or agent_pattern, so it lacks explicit alternatives or exclusions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.