Skip to main content
Glama

Draft release notes

draft_release_notes
Read-only

Categorise shipped work into breaking changes, features, improvements, fixes and internal work, then draft Markdown release notes from a tracker query or item list for human review before publishing.

Instructions

Categorise shipped work into breaking changes, features, improvements, fixes and internal work, then draft Markdown release notes. Pass a tracker query (source plus filters) or a list of items. Returns the draft plus a review list of items it excluded or could not place. Nothing is published: the draft is for a human to review.

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": "draft_release_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
jqlNoJira only: custom JQL. Overrides project, fixVersion and dates.
dateNoRelease date, YYYY-MM-DD.
repoNoGitHub only: repository as "owner/name".
teamNoLinear only: team key, e.g. "ENG".
wiqlNoAzure DevOps only: custom WIQL. Overrides project, iteration and dates.
itemsNoWork items to use instead of fetching from a tracker.
limitNoMaximum items to fetch (default 200, max 500).
sinceNoInclude work closed on or after this date (YYYY-MM-DD).
untilNoInclude work closed on or before this date (YYYY-MM-DD).
sourceNoWhich tracker to read from.
projectNoJira project key (e.g. "PAY") or Azure DevOps project name (e.g. "Payments").
versionNoRelease name or version, e.g. "v2.4.0".
audienceNocustomer: plain language, no internal work or ticket keys. internal: everything, with links.customer
iterationNoAzure DevOps only: iteration path, including child iterations, e.g. "Payments\Sprint 42".
fixVersionNoJira only: fix version, e.g. "2.4.0".
productNameNo
includeLinksNoShow ticket keys and links. Defaults on for internal, off for customer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral facts: the return value includes a review list of excluded or unplaceable items, and nothing is published. Auth requirements and rate limits for the external trackers are not mentioned, keeping it below a 5.

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?

Three sentences, each doing distinct work: what it produces, how to feed it, what comes back and what the safety posture is. The action and the non-publishing constraint are front-loaded with zero 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?

For a 17-parameter, no-output-schema tool this covers the essentials: input modes, return shape including the review list, and the no-publish guarantee. What is missing is how categorization decisions are made (heuristic vs. model) and any prerequisite such as tracker credentials, which matters for an openWorldHint 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 94%, so the baseline is 3 and the schema does most of the work. The description still adds real meaning by framing the 17 parameters as two mutually exclusive input modes (tracker query vs. explicit item list), which the flat schema does not make obvious. It does not elaborate on individual fields like audience or includeLinks, but those are well documented in the schema.

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?

Specific verb chain (categorise + draft) applied to a specific resource (release notes), with the taxonomy of categories spelled out. An agent knows exactly what output to expect (Markdown draft plus review list). It never names the sibling fetch_work_items, so it does not explicitly differentiate itself from the tool that only fetches work.

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

Usage Guidelines3/5

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

The description gives the two input modes (a tracker query of source plus filters, or a supplied item list), which implies when each is appropriate, and the closing sentence establishes the human-review context. It never states when NOT to use this tool or when to prefer fetch_work_items first, so routing is left to inference.

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