Skip to main content
Glama

Persistent Project Context for xAI Grok

by io.github.Wolfe-Jam
OverviewDiscussionsAdmin

Orchestrate Context Recommendation (FAF)

faf_orchestrate_recommendation
Read-onlyIdempotent

Takes raw content strings (.faf, .fafm, and optionally package.json/CHANGELOG.md/README.md) and runs deterministic drift + contradiction signals across the FAF substrate. Returns a structured Recommendation (recommend, severity, reason, summary) with hints containing the current effective_policy and partial[] for any stateful signals unavailable on the current surface. Light-lane execution (hosted) is WASM-pure with no filesystem access. Heavy-lane execution (local via bunx/rust-faf-mcp) has full FS + persisted state. Advisory only — never auto-fires.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fafNoRaw .faf YAML content (project DNA). Required for any meaningful analysis.
fafmNoRaw .fafm YAML content (memory layer). Enables drift detection.
readmeNoRaw README.md content. Enables README arch-tree cross-stamp checks.
changelogNoRaw CHANGELOG.md content. Enables changelog cross-stamp checks.
packageJsonNoRaw package.json content. Enables version cross-stamp checks (.faf vs pkg).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "content": {
-      "items": {
-        "properties": {
-          "text": {
-            "description": "Orchestration summary plus embedded Recommendation JSON.",
-            "type": "string"
-          },
-          "type": {
-            "const": "text",
-            "type": "string"
-          }
-        },
-        "required": [
-          "type",
-          "text"
-        ],
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "isError": {
-      "type": "boolean"
-    }
-  },
-  "required": [
-    "content",
-    "isError"
-  ],
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "content": {
+      "items": {
+        "properties": {
+          "text": {
+            "description": "Orchestration summary plus embedded Recommendation JSON.",
+            "type": "string"
+          },
+          "type": {
+            "const": "text",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "isError": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "content",
+    "isError"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already mark this read-only, idempotent, and non-destructive, and the description adds genuinely valuable behavioral context: hosted execution is WASM-pure with no filesystem access, local execution has full FS and persisted state, and the tool is advisory-only and never auto-fires. This clearly exceeds what the annotations alone provide.

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

Conciseness5/5

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

Every sentence in the description carries useful information: core behavior, output shape, execution-lane constraints, stateful-signal caveats, and safety semantics. It is dense but not bloated, and the most decision-relevant information is front-loaded.

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?

With no output schema available, the description compensates by defining the Recommendation shape and the hints fields. It also covers execution environments, state availability, and safety posture, making this definition sufficiently complete for an agent to understand the tool's contract.

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 the input schema already documents each parameter meaningfully. The description lists the accepted file types and frames them as inputs to drift/contradiction analysis, but it does not add substantial parameter behavior beyond the schema.

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 states a clear verb-resource relationship: it takes raw content strings, runs deterministic drift/contradiction signals, and returns a structured Recommendation. It is clearly legible and unlikely to be confused with a vague system tool, though it does not explicitly distinguish itself from closely related siblings like faf_analyze or faf_gate.

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?

The description implies when to use the tool by describing its orchestrated recommendation role and advisory nature, but it never explicitly says when to prefer this over alternatives. With 19 sibling tools, the absence of direct sibling positioning leaves the agent to infer the right selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Persistent Project Context for xAI Grok toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources