Skip to main content
Glama
Datris MCP Server

Datris MCP Server

run_doctor

Diagnose deployment health via self-checks covering Vault token expiry, secrets, model loading, disk/staging, version skew, and optional AI probes; failed checks include remediation steps.

Instructions

Run the platform's operational self-check and return a report: Vault token expiry, AI slot secrets complete, embedding model actually loaded, disk usage, the payload staging area (writable, room for one run, no orphaned run directories), component version skew, and (opt-in) whether each AI model answers. Each non-ok check carries a remediation command for the operator; nothing is changed. Do NOT call run_doctor as part of the normal workflow — it is slow. Only use it for diagnostics when something fails or the user asks about the deployment's health. Host-level checks (Docker volumes, container env drift) need datris doctor on the machine running Docker and are not included here.

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": "run_doctor"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo`full` (default) or `quick` (only the cheap startup-safe subset).
include_ai_probesNoAlso send a minimal request through each configured AI slot to confirm the key and model work (spends a few tokens). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the whole burden and does well: it states nothing is changed, that the tool is slow, that non-ok checks include remediation commands, and that AI probes spend tokens. Gaps remain around operator permissions required to run the checks and which credentials it needs to read Vault/AI secrets.

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 action and the check list, then the efficiency warning, then the host-level exclusion — a sensible order for an agent scanning it. It is dense (a long enumeration in one sentence) but nearly every clause adds a distinct, decision-relevant fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description conveys what a report contains, that failing checks come with remediation commands, and the cost/latency profile. Combined with the explicit scope exclusions, an agent has everything needed to decide whether and how to call it.

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% and both parameters already document `full` vs `quick` and the AI-probe behavior, including token spend. The description only adds the framing "(opt-in)" for the probe flag, so the baseline of 3 applies with little extra semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb+resource ("run the platform's operational self-check") and enumerates exactly what is checked: Vault token expiry, AI slot secrets, embedding model load, disk usage, payload staging area, version skew, and optional AI probes. It also scopes out host-level checks (Docker volumes, container env drift) as belonging to the `datris doctor` CLI. It does not distinguish itself from the sibling `check_service_health`, which an agent could plausibly confuse with a health-check tool, so it falls short of a 5.

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?

Explicit negative guidance ("Do NOT call run_doctor as part of the normal workflow — it is slow") and explicit positive triggers ("only use it for diagnostics when something fails or the user asks about the deployment's health"). It even routes the out-of-scope host-level checks to the correct alternative, `datris doctor` on the Docker host.

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