Skip to main content
Glama
Facebook Pages MCP Server

Facebook Pages MCP Server

by asrrin29

graph_batch

Read-onlyIdempotent

Run multiple Facebook Graph API requests in a single call to reduce round trips and combine Page post, comment, or media operations.

Instructions

Run several Graph API calls in one request Run a batch of Graph API requests in one call to save round trips. Each entry is {method, relative_url, name}, where relative_url is a Graph path such as '1001/posts'. GET entries are always allowed; POST and DELETE entries need the write permission. Graph API: POST batch. A batch entry without relative_url has no target, and Graph answers it as a request on the version root: 'Unsupported get request'.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "requests": "<requests>"
    },
    "name": "graph_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestsYes
access_tokenNoOptional Facebook Page access token for this call only. Use it when the token you hold is not the one this server was configured with, or when the configured token has expired. Takes effect for this call and nothing else. Also accepted as token or page_token.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.6.1

TDQS

B3.2/5.0
Behavior1/5

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

The description states that POST and DELETE entries are accepted and executed, i.e. the tool performs writes and at least one non-idempotent operation, directly conflicting with the supplied readOnlyHint=true and idempotentHint=true. An agent trusting the annotations could fire DELETE entries believing the call is a safe, repeatable read. The description does add useful edge-case behavior (an entry without relative_url is answered as an 'Unsupported get request' on the version root), but the core safety claim is contradicted.

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 opening two clauses are near-verbatim restatements ("Run several Graph API calls in one request" / "Run a batch of Graph API requests in one call"), so one of them is pure waste. The rest is dense and useful, but the batch-limit and response-shape concerns are absent while the duplicated opener survives. Front-loading the entry format earlier would improve scanability.

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 dispatcher with no output schema, the description should say what comes back — Graph returns a parallel array of {code, headers, body} per entry — and it does not. It also omits the platform's batch size cap, which materially affects how an agent chunks work. What it does cover (entry structure, permissions, missing-relative_url behavior) is solid but leaves the return contract and limits unspecified.

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

Parameters4/5

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

Schema coverage is 50%: the `requests` array item is an undescribed open object, and the description compensates by defining the entry keys (method, relative_url, name) and giving a concrete relative_url example such as '1001/posts'. It also explains the failure mode of a missing relative_url, which is pure added meaning. It does not explain what `name` is used for, and the `access_token` parameter's aliases are already documented in 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 names a specific capability: executing several Graph API calls inside one HTTP request, with an explicit entry shape {method, relative_url, name}. That is clearly distinguishable from the single-target siblings (page_get, post_get, page_posts_list) even though no sibling is named. It stops short of a 5 only because it never explicitly contrasts itself with running the individual tools once.

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?

"Run a batch ... in one call to save round trips" gives the motivating condition for choosing this tool over individual calls. It further states that GET entries are always allowed while POST and DELETE need write permission, which is real routing guidance. There is no explicit when-not-to-use or batching-threshold guidance (e.g. maximum entries per batch).

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