Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

causal_trace

Root Cause Analysis through memory: given a problem description, traces the causal chain from root cause through intermediate failures to the current symptom, then surfaces the exact solution that worked before. Read-only — does not modify any stored data. Requires prior learning: brain must have lessons stored via learn_from_attempts or brain_from_git. Returns an ordered chain of concepts with confidence scores plus the matching solution; returns an empty chain with a message if no causal path is found. Example: causal_trace(problem="auth breaks after restart") → "Root: k8s:namespace-terminating → keycloak:jwks-race → Solution: PollUntilContextTimeout 3min". Use recall_best_solution for direct topic lookup, syndicate_search for community patterns, and causal_trace when you have a symptom and need the full root-cause chain.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "problem": "<problem>"
    },
    "name": "causal_trace"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoOptional: narrow search to these tags
problemYesDescribe the problem or error you are seeing right now
max_depthNoMax causal chain depth to trace (default: 5)
instance_idNoUUID of the cache instance.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it declares 'Read-only — does not modify any stored data,' discloses the prerequisite dependency on prior learning, describes the return shape (ordered chain with confidence scores plus matching solution), and documents the empty-result behavior with a message. The worked example further anchors the output format.

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?

Dense but front-loaded: purpose first, then safety and prerequisites, then return shape, then the example and sibling routing. Every sentence earns its place, though the single unbroken paragraph packs a lot and could be slightly easier to scan as separate lines.

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 read-only retrieval tool with a fully documented four-parameter schema and no output schema, the description covers purpose, prerequisites, safety, return format, and failure mode. The only remaining gap is that it does not explain how max_depth or tags materially change results.

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 problem, tags, max_depth, and instance_id are already documented. The description adds only the framing of 'problem' as the symptom being observed, plus the example; it says nothing about tags scoping, depth tradeoffs, or what instance_id selects. Baseline 3 is appropriate.

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 chain and resource: 'traces the causal chain from root cause through intermediate failures to the current symptom, then surfaces the exact solution that worked before.' It also explicitly distinguishes itself from recall_best_solution and syndicate_search in the closing sentence, so an agent can route on name alone.

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?

Gives explicit routing: recall_best_solution for direct topic lookup, syndicate_search for community patterns, and causal_trace for when you have a symptom and need the full root-cause chain. It also states a hard precondition (must have lessons stored via learn_from_attempts or brain_from_git), which is exactly the kind of when-not guidance that prevents empty calls.

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.