Skip to main content
Glama

Compare two versions of an application

edgegap_compare_versions
Read-only

Compare two app versions from their running deployments to decide rollback or promote: error deployments, crash restarts, exit codes, and CPU/memory use versus requested limits, with differences spelled out.

Instructions

Compare two versions of one application from their running deployments, to back a rollback or promote decision: deployments in error, crash restarts and exit codes, and CPU and memory (average, p95, peak) against each version's requested cpu_units and memory_mb, with the differences spelled out. Reads up to 20 running deployments per version, newest first, so both versions need deployments running now (stopped ones keep no logs or status). Read-only.

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": {
      "application": "<application>",
      "version_a": "<version_a>",
      "version_b": "<version_b>"
    },
    "name": "edgegap_compare_versions"
  }
}

Input Schema

NameRequiredDescriptionDefault
version_aYesThe baseline version, e.g. the one in production.
version_bYesThe version to compare against it, e.g. the new build.
applicationYesApplication name.
max_deployments_per_versionNo1-20. Default 5.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.19.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds substantive behavior beyond them: it samples up to 20 running deployments per version, orders them newest first, and explains why stopped deployments are unusable (no logs or status). That is exactly the kind of data-source and sampling disclosure an agent needs before trusting the comparison.

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?

Front-loaded with the action and decision context, then a tight colon-list of compared signals, then the sampling limit. Every clause earns its place and there is no filler.

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 burden of return content, and it does list the compared dimensions and promises differences are 'spelled out.' It does not describe the response shape or how differences are present in the payload, which is the remaining gap for a comparison tool.

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 100%, so the baseline is 3, but the description adds real meaning by capping the read at 20 deployments per version, which clarifies max_deployments_per_version beyond the schema's misleadingly vast maximum. It also frames version_a/version_b as the baseline-versus-candidate pair, though the schema already covers that role labeling.

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 (compare) and resource (two versions of one application) plus the exact comparison payload: errors, crash restarts, exit codes, and CPU/memory average/p95/peak against requested cpu_units and memory_mb. An agent can tell this apart from single-deployment tools like edgegap_get_deployment_metrics without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit decision context ('to back a rollback or promote decision') and a real precondition ('both versions need deployments running now; stopped ones keep no logs or status'). It stops short of naming an alternative tool for when the precondition fails, so it is strong but not a full when/when-not/alternative map.

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