Skip to main content
Glama
Datris MCP Server

Datris MCP Server

list_incidents

List recovery-agent incidents newest first and filter by state to find active issues; each entry includes resource, diagnosis steps, and verdict.

Instructions

List the platform's recovery-agent incidents, newest first. An incident is opened by the platform itself when a scheduled tap finally fails, a pipeline job errors, a tap goes stale, a pipeline's volume swings, or a source changed its columns after a successful run (schema drift); the recovery agent diagnoses it and — within the agent policy's recovery mode — repairs and verifies it (for taps, re-running or fixing the tap; for pipelines, regenerating the stored AI script; the evidence names the script versions before and after). Each entry carries kind, resource, state (open | diagnosing | proposed | awaiting_approval | executing | verifying | resolved | failed | abandoned), classification, a step-by-step narrative, and — when the platform computed evidence for it — a verdict (pending | pass | fail | needs-human). Use state=open for what is being worked right now. Returns {enabled:false, incidents:[]} when the recovery agent is off.

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": "list_incidents"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum incidents to return (default 50).
stateNoFilter: open (any active state) or a specific state name. Omit for all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does most of it: it explains the incident lifecycle, the nine possible states, the verdict values, that evidence may or may not exist, and the exact degraded return of {enabled:false, incidents:[]}. It never states whether the call itself is a pure read or touches the recovery agent (e.g., triggering diagnosis), which is the one safety detail an agent would still want.

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 purpose and ordering, and the long clause explaining incident causes and repair actions is genuinely useful for interpreting results. The sentence is dense — heavy semicolon and parenthetical nesting — and some enumeration (script version evidence) could be trimmed without losing decision value.

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 describe returns, and it does: entry fields (kind, resource, state, classification, narrative, verdict) and the disabled-case payload. Combined with zero annotations, it covers enough to call the tool correctly; only pagination/limit-overflow behavior remains unstated.

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 coverage is 100%, so the baseline is 3, and the description does marginally more: it enumerates the concrete state names that the schema only calls "a specific state name" and clarifies that open means any active state. It adds no guidance on limit tuning or what happens when limit is exceeded.

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 and resource ("List the platform's recovery-agent incidents") plus ordering ("newest first"), then defines what an incident actually is (tap failure, pipeline error, schema drift, etc.). That definitional content separates it from generic listers and from list_pending_approvals, which an agent might otherwise conflate with the awaiting_approval state.

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 an actionable selection rule: "Use state=open for what is being worked right now," which resolves the main ambiguity of whether to filter or not. It also signals the tool is a no-op when the recovery agent is off. It stops short of naming an alternative tool for other incident-related needs, so it is clear context without explicit exclusions.

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

Deploy Server

Other Tools