Skip to main content
Glama

One release and its readiness, feature by feature, worked out from the board by the rules of D113 (never by AI).

get_release
Read-onlyIdempotent

One release and its readiness, feature by feature, worked out from the board by the rules of D113 (never by AI).

Feature = an epic in the release; issues with no epic are grouped as other. Each feature lists the checks it passes and, when it is not Ready, the reasons. For people who do not manage releases (manage: false) the gate items, baseline and scope history are left out — frontmatter.gate is [], baseline null, scope_log [] and gate / scope are null — only gate_summary is given, and added_after_baseline is false (D113 (4)). D198: everyone sees frontmatter.release_note and frontmatter.deployments; in the member view each deployment's notes is "" and build_url null. latest_deployments = what is live in each environment. Use the numbers as they are; do not guess.

Read this before answering anything about a release ("are we ready?", "what is blocked?", "summarise for the steering meeting"). Use status, features[] (status, checks, reasons), other, counts, gate_summary and scope exactly as returned — never guess, round or invent numbers, and name the issue keys from reasons. manage: false is the member view (no gate items, no scope history; each deployment's notes is "" and build_url null) — say so rather than guessing them. frontmatter.release_note is the customer-facing release note (apart from body, the internal description) and frontmatter.deployments the log of recorded deployments (D198); latest_deployments = what is live in each environment — report them as returned, never guess what is live. You may create a planned release (create_release) and edit its name, date, milestones and description until the baseline is locked (update_release), write its release note while it is planned, and record deployments (add_release_deployment), with your user's rights (D189, D198). You cannot tick its gate, lock its baseline, mark it shipped, reopen or delete it: that is for people in the web app — an AI agent never approves a release.

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": {
      "project_key": "<project_key>",
      "release_id": "<release_id>"
    },
    "name": "get_release"
  }
}

Input Schema

NameRequiredDescriptionDefault
release_idYesRelease id (spec D113): `R-` + a number, unique in its project; the file is `releases/R-{n}.md`.
project_keyYesProject key, e.g. `KJ`. 2–10 chars, uppercase letters and digits, starts with a letter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond readOnlyHint/idempotentHint, the description discloses the permission-dependent view shape (manage:false drops gate items, baseline, scope_log, sets added_after_baseline false, blanks deployment notes and build_url), the D198 release_note/deployments visibility, and the hard limits on what an agent may write. That is substantial behavior an agent could not infer from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and field semantics, which is good, but the member-view (`manage: false`) behavior is explained twice in near-identical terms, and the title sentence is repeated verbatim as the opening line. The write-permission paragraph is also dense with parenthetical spec citations that slow an agent down.

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?

There is no output schema, so the description carries the full burden of describing the return shape, and it does: `status`, `features[]` with checks and reasons, `other`, `counts`, `gate_summary`, `scope`, `frontmatter.release_note` / `deployments`, and `latest_deployments`. It also instructs the agent never to guess or round those numbers.

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 both parameters (release_id with its R-n pattern and file location, project_key with its format) are fully documented in the schema. The description adds no format or validation meaning to either parameter, so baseline 3 applies.

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 first sentences state a specific verb and resource (read one release's readiness, feature by feature, computed from the board by D113 rules) and define what a feature is (an epic in the release, no-epic issues grouped as `other`). This clearly separates it from `list_releases` (enumeration) and `update_release` (mutation).

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?

Explicit trigger phrases are given ('are we ready?', 'what is blocked?', 'summarise for the steering meeting'), plus explicit routing to alternatives: create_release / update_release / add_release_deployment for the writable operations, and the web app for gate ticking, baseline locking, shipping and deletion. It also states a negative rule (an AI agent never approves a release).

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