Skip to main content
Glama
adrianczuczka

mason

by adrianczuczka
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

review_advisory

Assess a repair advisory against its repo scope, then record outcomes as addressed, inapplicable, deferred, or dismissed. Tracks review token, reviewer, and notes; content changes reopen reviews while unrelated commits preserve them.

Instructions

Prepare an assessment of an original repair advisory and its exact repository scope, then record authorized addressed, inapplicable or deferred outcomes with reviewToken, reviewer and note. Relevant changes reopen reviews; unrelated commits preserve them. Records belong in Git. Decision findings route to review_decision; this tool never approves decisions. Recorded identities are assertions, not authenticated approvals. For dependency advisories, action dismiss with reasonCode and note records a one-step dismissal without a token or reviewer. no-dependency-claims reopens only on document content changes; unrelated-manifest-change also tracks scoped manifests.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dirYesAbsolute path to the project root
noteNo
actionNoprepare
reviewerNo
findingIdYes
reasonCodeNo
reviewTokenNo
baselinePathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.19.1
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "prepare",
-  "addressed",
-  "inapplicable",
-  "deferred"
-]New value: +[
+  "prepare",
+  "addressed",
+  "inapplicable",
+  "deferred",
+  "dismiss"
+]
    • addedInput schema / properties / reasonCode
      Added value: +{
+  "enum": [
+    "no-dependency-claims",
+    "unrelated-manifest-change"
+  ],
+  "type": "string"
+}
  2. Addedv0.17.0

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations provided, the description carries full behavioral weight and does so well. It discloses that records belong in Git, that recorded identities are assertions rather than authenticated approvals, that relevant changes reopen reviews while unrelated commits preserve them, and that dismiss is a one-step dependency-specific action.

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 description is dense but mostly purposeful, front-loading the core purpose before adding behavioral caveats. Some sentences are long and semicolon-heavy, making parsing harder, but no sentence is pure filler.

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?

The description provides substantial behavioral context for a complex tool with no annotations or output schema, including reopen rules and identity caveats. However, it lacks a clear mapping of the eight parameters to the five action values, does not define what 'prepare' produces, and does not describe return values or outcomes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 13%, and the description only partially compensates. It mentions reviewToken, reviewer, note, dismiss, and reasonCode with some context, but it does not clarify the required parameters dir, baselinePath, and findingId beyond minimal schema text, nor does it map which parameters are needed for each action.

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 description uses specific verbs and resources: 'prepare an assessment', 'record authorized addressed, inapplicable or deferred outcomes', and explicitly says this tool never approves decisions. It clearly distinguishes itself from review_decision while naming the exact review workflow it supports.

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 description routes decision findings to review_decision and explicitly states this tool never approves decisions, providing a clear exclusion. It also gives specific usage branches for dependency advisories with reasonCode, though it does not enumerate all alternative sibling tools or all conditions for choosing them.

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