Skip to main content
Glama

Check a changelog against Keep a Changelog

validate_changelog
Read-onlyIdempotent

Check a CHANGELOG.md against Keep a Changelog 2.0.0: version headings, YYYY-MM-DD dates, newest-first order, the six types of change, breaking-change markers, Unreleased, reference links. Returns each problem with its line number and fix, plus a corrected copy with the safe fixes applied. Pass the text, or a public GitHub repository or changelog file URL.

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": "validate_changelog"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoA public github.com repository (its CHANGELOG.md is found for you) or a changelog file URL on github.com or raw.githubusercontent.com. Use this or markdown.
markdownNoThe changelog text, e.g. the contents of CHANGELOG.md. Use this or url.
file_nameNoThe file's name when it isn't CHANGELOG.md, e.g. "HISTORY.md".
include_fixedNoInclude the corrected copy. Default true.
repository_urlNogithub.com or gitlab.com repository the changelog belongs to, so missing version links can be written. Not needed with url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

With only readOnlyHint/openWorldHint/idempotentHint supplied and no output schema, the description carries the important remaining load: it discloses that results are per-problem with a line number and a fix, and that a corrected copy is produced with only the safe fixes applied. That 'safe fixes' qualifier meaningfully bounds how much mutation the tool will suggest. It stops short of covering failure modes such as private repos, oversized files, or what happens when neither text nor URL is supplied.

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?

Two sentences, both earning their place: the first front-loads the thing being validated plus the checklist, the second delivers the return contract and the accepted input forms. The long colon-delimited enumeration reads as a scannable list rather than padding, and nothing is restated twice.

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 five-parameter, zero-required tool with no output schema, the description does the heavy lifting well by explaining both the diagnostics and the corrected-copy return. The one real gap is that it never states the implicit constraint that at least one of markdown or url is effectively mandatory, so an agent could call it with neither.

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 all five parameters are already documented in structured data and the baseline is 3. The description reiterates the text/URL duality but adds nothing on file_name, include_fixed, or repository_url, which is why it cannot rise above the baseline here.

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 and resource ('Check a CHANGELOG.md against Keep a Changelog 2.0.0') and then enumerates the concrete rules enforced — version headings, YYYY-MM-DD dates, newest-first order, six change types, breaking-change markers, Unreleased, reference links. An agent can immediately distinguish this from convert_changelog, get_changelog, or compare_versions because the validation scope is spelled out rather than implied.

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?

The final sentence makes the invocation context explicit: supply raw text, or point at a public GitHub repository or changelog file URL, and get problems plus a corrected copy back. What is missing is any explicit exclusion or routing advice — it never says to reach for convert_changelog instead when the goal is reformatting rather than diagnosing, so the agent must infer that boundary from the sibling name alone.

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.

Resources