Skip to main content
Glama
adrianczuczka

mason

by adrianczuczka
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mason_init

Inspect this project now: returns documentation audit findings, committed-diff review findings, decision/map status, and a quickstart playbook. Quickstart is read-only and deterministic.

Instructions

Inspect this project now: returns documentation audit findings, committed-diff review findings, decision/map status, and a quickstart playbook. Quickstart is read-only and deterministic. Explicit mode: setup validates shared configuration and activates locally without editing shared files; mode: init explicitly prepares MCP, instructions and lifecycle hooks for review and commit. Neither runs audits or prepares repairs; use only when requested. Optional host selects codex or claude. Optional base selects the review comparison; evidence imports CI manifests with check outcomes, commit freshness, and links to changed files and accepted decisions. Repeat calls refresh findings even after setup.

Input Schema

NameRequiredDescriptionDefault
dirYesAbsolute path to the project root directory
baseNoQuickstart only: Git ref for committed-diff review. Defaults to the first available main branch ref.
hostNoAssistant to configure in init/setup mode; inferred only when unambiguous.
modeNoQuickstart inspects without edits; init prepares shared configuration; setup activates compatible configuration locally.quickstart
dryRunNoInit only: preview shared configuration changes without writing files.
evidenceNoQuickstart only: repository-local CI evidence manifests to include in the review. Imports Vitest JSON, SARIF, and native-validator mason-check-json results without executing check commands.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.22.0
    • changedInput schema / properties / base / description
      Previous value: -"Git ref for committed-diff review. Defaults to the first available main branch ref."New value: +"Quickstart only: Git ref for committed-diff review. Defaults to the first available main branch ref."
    • addedInput schema / properties / dryRun
      Added value: +{
+  "description": "Init only: preview shared configuration changes without writing files.",
+  "type": "boolean"
+}
    • changedInput schema / properties / evidence / description
      Previous value: -"Repository-local CI evidence manifests to include in the review. Imports Vitest JSON, SARIF, and native-validator mason-check-json results without executing check commands."New value: +"Quickstart only: repository-local CI evidence manifests to include in the review. Imports Vitest JSON, SARIF, and native-validator mason-check-json results without executing check commands."
    • changedInput schema / properties / host / description
      Previous value: -"Assistant to configure in setup mode; inferred only when unambiguous."New value: +"Assistant to configure in init/setup mode; inferred only when unambiguous."
    • changedInput schema / properties / mode / description
      Previous value: -"Quickstart inspects without edits; map requests an architecture build; setup installs the shared onboarding flow."New value: +"Quickstart inspects without edits; init prepares shared configuration; setup activates compatible configuration locally."
    • changedInput schema / properties / mode / enum
      Previous value: -[
-  "quickstart",
-  "map",
-  "setup"
-]New value: +[
+  "quickstart",
+  "init",
+  "setup"
+]
  2. Addedv0.17.0

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden. It discloses that quickstart is read-only and deterministic, setup activates locally without editing shared files, init prepares MCP/instructions/lifecycle hooks for review and commit, evidence imports CI manifests without executing checks, and repeat calls refresh findings. It still does not explicitly state permissions, reversibility, or exactly what init/setup write, but adds substantial context.

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?

The description is front-loaded with 'Inspect this project now' and covers many relevant aspects, but it is dense and clause-heavy. Ambiguous phrasing such as 'Neither runs audits or prepares repairs' detracts from clarity even though the content is mostly purposeful.

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?

For a complex multi-mode tool with no annotations and no output schema, the description covers mode behavior and quickstart returns, which is helpful. However, it omits setup/init return values, error behavior, and explicit sibling routing, leaving important gaps for an agent deciding whether and how to call it.

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 the baseline is 3. The description reiterates the meaning of host, base, mode, and evidence and adds a little detail about evidence imports, but it does not provide syntax or selection guidance beyond what the schema already supplies.

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?

The description gives a specific verb ('Inspect') and enumerates the outputs (documentation audit findings, committed-diff review findings, decision/map status, quickstart playbook), then distinguishes quickstart, setup, and init modes. It does not differentiate itself from sibling tools such as mason_complete_init or get_snapshot, so it falls short of a 5.

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 provides mode-level context: quickstart is read-only, setup validates config locally, and init prepares MCP/instructions/hooks. However, it never names alternative tools or clearly states when to choose each mode over the others, offering only a vague 'use only when requested' and 'neither runs audits or prepares repairs' as usage constraints.

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