Skip to main content
Glama
Deviank88

KnowledgeRail

by Deviank88
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

knowledge_admin

Destructive

Set up, maintain, and diagnose project workspaces for AI agents. Handle initialization, linting, migration, and usage audits to keep documentation reliable.

Instructions

Workspace setup, maintenance and diagnostics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
forceNolint: repair nested wiki.
pathsNo
scopeNo
actionYesinit=bootstrap;checkpoint=rebuild;usage=stats/audit/reset;semantic_setup=models;consolidate=review;client_setup=hooks;lint=broken links/orphan pages;migrate=upgrade.
backupNo
run_idNo
clientsNo
dry_runNolint: false applies repair.
optionsNousage: action=status|audit|reset|outcome; audit accepts days(1..30), max_turns(1..100), client(codex|claude); outcome requires outcome=succeeded|failed. semantic_setup:{model};consolidate:{days,proposals}.
setup_modeNopreview
integrity_modeNometadata
target_versionNo4
include_missingNo
include_orphansNo
migration_actionNoplan
include_broken_linksNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
stateYes
guidanceNo
nextActionYes
resultTextNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.9.1
    • changedInput schema / properties / action / description
      Previous value: -"init=bootstrap;checkpoint=rebuild;usage=stats/reset;semantic_setup=models;consolidate=review;client_setup=hooks;lint=broken links/orphan pages;migrate=upgrade."New value: +"init=bootstrap;checkpoint=rebuild;usage=stats/audit/reset;semantic_setup=models;consolidate=review;client_setup=hooks;lint=broken links/orphan pages;migrate=upgrade."
    • changedInput schema / properties / options / description
      Previous value: -"usage:{action:status|reset|outcome,outcome:succeeded|failed};semantic_setup:{model};consolidate:{days,proposals}."New value: +"usage: action=status|audit|reset|outcome; audit accepts days(1..30), max_turns(1..100), client(codex|claude); outcome requires outcome=succeeded|failed. semantic_setup:{model};consolidate:{days,proposals}."
  2. Changed4 schema fields changedv2.9.0
    • changedInput schema / properties / action / description
      Previous value: -"init=bootstrap;status=state;checkpoint=rebuild;client_setup=hooks;lint=validate links/repair;drift=anchors;migrate=upgrade."New value: +"init=bootstrap;checkpoint=rebuild;usage=stats/reset;semantic_setup=models;consolidate=review;client_setup=hooks;lint=broken links/orphan pages;migrate=upgrade."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "init",
-  "status",
-  "checkpoint",
-  "client_setup",
-  "lint",
-  "drift",
-  "migrate"
-]New value: +[
+  "init",
+  "status",
+  "checkpoint",
+  "usage",
+  "semantic_setup",
+  "consolidate",
+  "client_setup",
+  "lint",
+  "drift",
+  "migrate"
+]
    • addedInput schema / properties / options
      Added value: +{
+  "additionalProperties": {},
+  "description": "usage:{action:status|reset|outcome,outcome:succeeded|failed};semantic_setup:{model};consolidate:{days,proposals}.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
    • removedOutput schema / additionalProperties
      Removed value: -true
  3. Changed3 schema fields changedv2.7.2
    • changedInput schema / properties / action / description
      Previous value: -"init=bootstrap;status=state;checkpoint=rebuild;client_setup=hooks;lint=validate links;drift=anchors;migrate=upgrade stored knowledge format."New value: +"init=bootstrap;status=state;checkpoint=rebuild;client_setup=hooks;lint=validate links/repair;drift=anchors;migrate=upgrade."
    • addedInput schema / properties / dry_run / description
      Added value: +"lint: false applies repair."
    • addedInput schema / properties / force / description
      Added value: +"lint: repair nested wiki."
  4. First observedv2.7.0

TDQS

D1.6/5.0
Behavior2/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this tool mutates state. The description adds nothing beyond a generic category; it does not disclose any specific behavioral traits, such as whether certain actions require confirmations, what gets affected, or any side effects.

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

Conciseness2/5

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

The description is a single sentence, so it is structurally simple, but it is under-specification rather than conciseness. It omits essential information and does not earn its place as a useful summary.

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

Completeness1/5

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

Given the tool's high complexity (16 parameters, nested objects, multiple enums, an output schema), the description is grossly inadequate. It does not explain what the tool returns, what actions are available, or how to invoke it correctly. The agent cannot use this tool effectively based on this description.

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

Parameters1/5

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

With only 25% schema description coverage, the description should compensate by explaining key parameters, but it says nothing. The 16-parameter schema is complex with enums and nested objects, and the description provides zero guidance on how to use any parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a broad category ('Workspace setup, maintenance and diagnostics') rather than a specific verb and resource. It gives a general idea but no concrete action, and it does not differentiate from sibling tools like knowledge_ingest or knowledge_page. It is vague and could apply to many tools.

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

Usage Guidelines1/5

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

There is no guidance on when to use this tool versus its siblings, nor any mention of prerequisites, contexts, or exclusions. The description provides no decision-making information for an agent.

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