Skip to main content
Glama

Summarise the health of running deployments

edgegap_fleet_health
Read-only

Check current health across running Edgegap deployments in one call: status counts, error details, deployments stuck starting over 10 minutes, unhealthy totals by location/version, and optional crash data.

Instructions

One call for "is anything wrong right now?" across running deployments, instead of checking them one by one: counts by status, the deployments in error with their error detail, ones stuck starting for over 10 minutes, and totals per location and per version with unhealthy ones flagged. check_crashes: true also reads each deployment's crash data (restarts, exit codes). Covers what Edgegap still lists: stopped deployments are gone, so this is current state, not history. Inspects up to 100 deployments per call, newest first. Read-only. Next: edgegap_search_deployment_logs for what the errors say, edgegap_compare_versions for a rollback decision.

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": "edgegap_fleet_health"
  }
}

Input Schema

NameRequiredDescriptionDefault
versionNoOnly this version (needs application).
applicationNoOnly this application. Default: all.
check_crashesNoAlso read crash data (restart count, exit code) per deployment. Default false.
max_deploymentsNoHow many to inspect, 1-100. Default 50.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.19.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description confirms read-only operation. Beyond that it discloses non-obvious behavior the schema cannot: only deployments Edgegap still lists are covered (stopped deployments are gone, so results are current state, not history), inspection is capped at 100 and ordered newest-first, and check_crashes triggers an extra read per deployment with a cost implication. It stops short of describing pagination or failure modes, but that gap is minor.

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 core question and the contents of the report before any caveats, and every sentence carries information. The first sentence is long and clause-heavy, bundling four distinct output categories, which slightly reduces scannability but nothing is filler.

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?

With no output schema, the description carries the return-value burden and does so: it enumerates what the summary contains and how unhealthy entries are flagged. Combined with the retention warning, the 100-deployment cap, default ordering, and the named next steps, an agent has everything needed to call this correctly and interpret the result.

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 every parameter is already documented in the input schema, and the one parameter the description elaborates (check_crashes reading restart counts and exit codes) largely restates the schema's own wording. It does not clarify the application/version dependency or how max_deployments interacts with the 100 cap. Baseline 3 is appropriate where the schema does the work.

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 concrete job: aggregate health summary across running deployments, enumerated precisely as counts by status, errored deployments with detail, deployments stuck starting over 10 minutes, and totals per location/version with unhealthy flagged. It explicitly frames itself against the alternative of checking deployments one by one, which separates it from edgegap_list_deployments and edgegap_get_deployment.

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?

Opens with the exact question the tool answers ("is anything wrong right now?") and names its alternatives: rather than checking deployments individually, call this one. It also routes onward with named siblings — edgegap_search_deployment_logs for error content and edgegap_compare_versions for a rollback decision — so the agent knows both the entry condition and the follow-up path.

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