Skip to main content
Glama
dave1362

RCA-MCP Connector

rca_analysis_batch

Run root cause analysis across multiple incidents at once, then rank recurring causes to identify systemic issues behind similar failures.

Instructions

Run the same RCA model over multiple incidents in one call, then rank which root causes recur most often across all of them — use this to spot a systemic cause behind several similar incidents, not just one.

Requires Starter+ (Free plan cannot batch at all; Starter allows up to 5 incidents per call, Pro+ up to 20 — call rca_admin_show_plan_info to check your own limit). For a single incident, use rca_analysis_run instead — it's simpler and doesn't need the plan tier.

Args: params (BatchAnalysisInput): - model_id: an existing model, applied identically to every incident - incidents: 1-20 payload dicts (capped by your plan), each matching the same shape rca_analysis_run expects for this model family

Returns: str: JSON {per_incident: [{incident_index, result_id, top_cause, confidence}, ...], cross_incident_ranking}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.1.15
    • addedInput schema / $defs / BatchAnalysisInput / properties / client_id / description
      Added value: +"Client namespace ID"
    • addedInput schema / $defs / BatchAnalysisInput / properties / token / description
      Added value: +"API key to authenticate this request"
  2. Changed1 schema field changedv4.1.14
    • changedInput schema / $defs / BatchAnalysisInput / properties / incidents / description
      Previous value: -"List of payload dicts (one per incident), max 20"New value: +"1-20 payload dicts (capped by your plan's max_batch_size), one per incident. Each must match the shape rca_analysis_run expects for this model family, e.g. for time-series families: {\"data\": {var: [values, ...], ...}, \"target\": \"var_name\"}"
  3. First observedv4.1.13

TDQS

A4.6/5.0
Behavior4/5

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

Annotations are all false/neutral, so the description carries the behavioral burden. It discloses plan gating, the identical application of the model across incidents, and the per-incident plus cross-incident ranking output. It stops slightly short of stating side effects such as whether results are persisted or whether a failing incident fails the whole batch, which would make it fully transparent.

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 organized into purpose, prerequisites, alternative, args, and returns. It is detailed yet each sentence earns its place, and the most important scope information is front-loaded.

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 batch operation with plan limits and cross-references to another tool, the description covers purpose, usage, limits, parameter meaning, and return shape. The only gap is the lack of error behavior for partially invalid batches, but the presence of an output schema and the detailed Returns section makes this a minor omission.

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 coverage is marked low, but the description compensates for model_id and incidents by explaining 'applied identically to every incident' and 'matching the same shape rca_analysis_run expects.' It does not add much for token/client_id, but those are sufficiently described in the schema and are less decision-critical.

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 opens with a concrete verb and resource: 'Run the same RCA model over multiple incidents in one call' and states the output's purpose (ranking recurring root causes to spot systemic issues). It clearly distinguishes from the sibling rca_analysis_run by specifying the batch-vs-single-incident scope.

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?

It gives explicit when-to-use guidance: 'use this to spot a systemic cause behind several similar incidents' and explicitly routes single-incident use to rca_analysis_run. It also gives plan-tier constraints and names rca_admin_show_plan_info as the way to check limits.

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