Skip to main content
Glama

Health & metrics

health
Read-only

Diagnose server slowness, errors, and security warnings by reporting version, workspace, caches, queues, running shells, latency, snapshots, and audit status.

Instructions

Server diagnostics: version, workspace, security posture and warnings, caches, queue, running shells, latency, snapshot store, audit status. Use when: you debug slowness or errors, or want the security warnings before risky work. include_audit=false skips the audit query. Avoid when: normal file work. Output: One key per report section (see sections); with sections set, also sections_requested and sections_unknown.

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": "health"
  }
}

Input Schema

NameRequiredDescriptionDefault
sectionsNoReport sections to return: notice, server, corehost, capability, queue, caches, shells, approvals, warnings, posture, snapshots, secrets, network, metrics, cache, trace, shell, environment, audit. caches/shells are live state; cache/shell are configuration. Omit for everything; use it when the full payload does not fit the response.
include_auditNotrue includes the audit-log summary in the result (default true); false skips the audit DB query.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv4.5.0
    • removedInput schema / properties / include_audit / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "maximum": 1,
      -    "minimum": 0,
      -    "type": "integer"
      -  }
      -]
    • changedInput schema / properties / include_audit / description
      Previous value: -"1 includes the audit-log summary in the result (default 1); 0 skips the audit DB query."New value: +"true includes the audit-log summary in the result (default true); false skips the audit DB query."
    • removedInput schema / properties / include_audit / maximum
      Removed value: -1
    • removedInput schema / properties / include_audit / minimum
      Removed value: -0
    • changedInput schema / properties / include_audit / type
      Previous value: -"integer"New value: +"boolean"
  2. Addedv4.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the cost/caching behavior that matters here — that include_audit triggers an audit DB query that can be skipped, and that the full payload may not fit the response so sections should be narrowed. It stops short of stating payload size or relative expense of the live-state sections, which would be the last piece of behavioral context for a diagnostics call.

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?

The structure is front-loaded and scannable: scope list first, then Use when, Avoid when, and Output. The section enumeration in the first line and the parenthetical '(see sections)' are slightly redundant with the schema, but nothing is verbose or padding.

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?

With no output schema, the description carries the return-value burden and does explain the shape: one key per report section, plus sections_requested and sections_unknown when sections is supplied. Combined with the schema's authoritative list of valid section names, an agent has enough to call it and interpret the result, though it doesn't say what a section looks like or how warnings are formatted.

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%, and the schema already explains that sections selects report sections and that include_audit=false skips the audit DB query. The description largely restates that ('include_audit=false skips the audit query') rather than adding new format or interaction detail, so the baseline 3 applies even though the restatement usefully reinforces the tradeoff.

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 names a specific resource (server diagnostics) and enumerates its scope: version, workspace, security posture and warnings, caches, queue, running shells, latency, snapshot store, audit status. This is clearly distinct from siblings like read_audit or shell_run, which cover only one of those sections, so an agent can pick this as the aggregate diagnostic tool without opening a schema.

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 an explicit 'Use when' (debugging slowness or errors, checking security warnings before risky work) and an explicit 'Avoid when' (normal file work), plus a parameter-level routing hint that include_audit=false skips the audit query. That covers both the positive trigger and the exclusion that keeps the agent out of this heavyweight tool during routine work.

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