Skip to main content
Glama
Sign In

AdsAgent — Meta Ads MCP

by md.adsagent
OverviewDiscussionsAdmin

fb_users_list

Read-only

Read stored FB labels/status/expiry/routing, never credentials; filter then paginate. refresh rereads rows; no Meta sync, token refresh, queued work or snapshot writes. BM: assets_lookup_business_links. Access is not full Settings. Use the same AdsAgent account

Input Schema

NameRequiredDescriptionDefault
limitNo
cursorNo
searchNo
refreshNo
fb_user_labelNo

Output Schema

NameRequiredDescriptionDefault
messageNo
retryableNo
support_refNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / connection_context
      Removed value: -{
-  "pattern": "^mctx_v1_[0-9a-f]{64}$",
-  "type": "string"
-}
  2. Changed1 schema field changed
    • addedOutput schema / else / properties / items / items / properties / connection_state
      Added value: +{
+  "description": "Optional. user_disconnected = the user withdrew AdsAgent's access (data is kept, reconnect any time); needs_reauthorization = the credential expired or was invalidated.",
+  "enum": [
+    "connected",
+    "user_disconnected",
+    "needs_reauthorization",
+    "removed"
+  ],
+  "type": "string"
+}
  3. Changed6 schema fields changed
    • addedOutput schema / then / properties / category
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / then / properties / expected
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / then / properties / failure_kind
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / then / properties / responsibility_hint
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / then / properties / route
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / then / properties / user_visible
      Added value: +{
+  "type": "boolean"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / connection_context
      Added value: +{
+  "pattern": "^mctx_v1_[0-9a-f]{64}$",
+  "type": "string"
+}
  5. Changed7 schema fields changed
    • addedOutput schema / $defs
      Added value: +{
+  "s0": {
+    "properties": {
+      "count": {
+        "type": "integer"
+      },
+      "has_more": {
+        "type": "boolean"
+      },
+      "items": {
+        "items": {
+          "properties": {
+            "id": {
+              "type": "string"
+            },
+            "name": {
+              "type": [
+                "null",
+                "string"
+              ]
+            }
+          },
+          "required": [
+            "id"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "count",
+      "items",
+      "has_more"
+    ],
+    "type": "object"
+  },
+  "s3": {
+    "properties": {
+      "status": {
+        "enum": [
+          "requires_validation",
+          "awaiting_assets",
+          "blocked"
+        ],
+        "type": "string"
+      },
+      "summary": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "status",
+      "summary"
+    ],
+    "type": "object"
+  }
+}
    • addedOutput schema / else / properties / refresh_meta / properties / created_at
      Added value: +{
+  "type": [
+    "null",
+    "string"
+  ]
+}
    • addedOutput schema / else / properties / refresh_meta / properties / finished_at
      Added value: +{
+  "type": [
+    "null",
+    "string"
+  ]
+}
    • addedOutput schema / else / properties / refresh_meta / properties / launch_readiness
      Added value: +{
+  "$ref": "#/$defs/s3"
+}
    • addedOutput schema / else / properties / refresh_meta / properties / refresh_summary
      Added value: +{
+  "properties": {
+    "failed_connections": {
+      "items": {
+        "properties": {
+          "label": {
+            "type": "string"
+          },
+          "reason": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "label",
+          "reason"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "failed_connections_count": {
+      "type": "integer"
+    },
+    "failed_connections_has_more": {
+      "type": "boolean"
+    },
+    "launch_readiness": {
+      "$ref": "#/$defs/s3"
+    },
+    "observed_at": {
+      "type": [
+        "null",
+        "string"
+      ]
+    },
+    "routing_errors": {
+      "type": "integer"
+    },
+    "scope": {
+      "enum": [
+        "tenant",
+        "fb_user"
+      ],
+      "type": "string"
+    },
+    "updated_assets": {
+      "properties": {
+        "ad_accounts": {
+          "$ref": "#/$defs/s0"
+        },
+        "businesses": {
+          "$ref": "#/$defs/s0"
+        },
+        "pages": {
+          "$ref": "#/$defs/s0"
+        }
+      },
+      "required": [
+        "ad_accounts",
+        "pages",
+        "businesses"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "observed_at",
+    "scope",
+    "updated_assets",
+    "failed_connections",
+    "launch_readiness"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}
    • addedOutput schema / else / properties / refresh_meta / properties / requested_scope
      Added value: +{
+  "enum": [
+    "tenant",
+    "fb_user"
+  ],
+  "type": "string"
+}
    • addedOutput schema / else / properties / refresh_meta / properties / started_at
      Added value: +{
+  "type": [
+    "null",
+    "string"
+  ]
+}
  6. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Goes meaningfully beyond the readOnly/openWorld annotations: it discloses that rows are stored (not live Meta data), that no token refresh, queued work or snapshot writes occur, and that 'refresh' merely rereads rows. These are exactly the side-effect boundaries an agent needs. It stops short of stating pagination limits or ordering behavior.

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?

Very short and front-loads the core read-scope statement, but it is written in dense telegraphic fragments ('BM: assets_lookup_business_links', 'Access is not full Settings') that cost more parsing effort than the words saved. Several clauses are ambiguous rather than economical.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile. However, with five parameters at zero schema coverage and an unresolved 'BM'/'Settings' aside, the description leaves real gaps an agent must guess around before calling.

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 coverage is 0%, so the description carries the burden. It does explain 'refresh' (rereads rows) and maps 'filter'/'paginate' to search and limit/cursor, and 'labels' hints at fb_user_label, but limit bounds, cursor semantics and search matching rules are all left undocumented.

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?

States the resource and what is read (stored FB labels/status/expiry/routing) and that credentials are never returned, which lets an agent distinguish it from fb_users_update_label or fb_users_refresh_routing. The verb is oblique ('Read stored...') and never plainly says 'list Facebook users', relying on the tool name and title to fill that in.

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?

'filter then paginate' and 'no Meta sync, token refresh, queued work or snapshot writes' give useful negative scoping, so an agent knows not to expect a live sync. But there is no explicit 'use this when X, use sibling Y instead', and cryptic fragments like 'BM: assets_lookup_business_links' and 'Access is not full Settings' leave the routing to inference.

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

All AdsAgent — Meta Ads MCP 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