Skip to main content
Glama

pr_description_lint

Read-onlyIdempotent

Deterministic PR description quality linter: flags a missing/too-short body, absent test evidence, absent stated rationale, an unstructured long body, and - only for PRs that look like bugfixes (title prefix fix/bug/hotfix/patch, or an explicit is_bugfix flag) - missing repro steps. Optionally requires a linked issue/ticket reference. Single PR only, no batch. Deterministic, no LLM.

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": {
      "pr": "<pr>"
    },
    "name": "pr_description_lint"
  }
}

Input Schema

NameRequiredDescriptionDefault
prYes{title?, body?, is_bugfix?}. is_bugfix overrides title-based inference when supplied.
require_issue_linkNoDefault false. When true, flags a missing issue/ticket reference in the title or body.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / pr / properties / body / description
      Added value: +"PR description, markdown."
    • addedInput schema / properties / pr / properties / body / maxLength
      Added value: +50000
    • addedInput schema / properties / pr / properties / is_bugfix / description
      Added value: +"Whether the PR fixes a bug; inferred from the title if omitted."
    • addedInput schema / properties / pr / properties / title / description
      Added value: +"PR title."
    • addedInput schema / properties / pr / properties / title / maxLength
      Added value: +500
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive/closed-world, and the description adds real value on top: the rule set, the bugfix inference trigger (title prefixes fix/bug/hotfix/patch), and the "deterministic, no LLM" guarantee. The notable gap is that with no output schema, it never says what a finding or result looks like.

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?

The check list is front-loaded and the scope/determinism caveats come last, which is the right order. Minor waste: "Deterministic" appears twice (opening and closing), and the middle sentence is dense with dashes, but nothing is genuinely extraneous.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Inputs are fully specified and the lint rules are exhaustive, but with no output schema the description should describe the return shape (list of findings? pass/fail? severities?) and it does not. For a linter whose entire value is the report it produces, that is a meaningful omission.

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; the description earns an extra point by disclosing the actual title prefixes used for bugfix inference and clarifying that is_bugfix overrides that inference. It also explains that require_issue_link searches title or body, matching the schema but reinforcing the semantics.

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?

Opens with a specific verb+resource ("PR description quality linter") and then enumerates the exact checks it performs: missing/too-short body, absent test evidence, absent rationale, unstructured long body, missing repro steps for bugfixes. The narrow 'PR description' scope cleanly separates it from siblings like commit_hygiene, story_lint, and ticket_lint, so an agent can select it 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 Guidelines3/5

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

It gives scope constraints ("Single PR only, no batch") and spells out the conditional bugfix path, which helps an agent decide when the tool applies. However, it never states when to reach for this versus the adjacent linters, nor any preconditions such as running it before opening a PR.

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.