Skip to main content
Glama
Sign In

Desearch

by io.github.Desearch-ai
OverviewDiscussionsAdmin

Facebook

facebook
Read-only

Read public Facebook data with Desearch. Set action and that action's arguments. search (query; optional count, cursor) and hashtag (tag; optional count, cursor) return Meta Ad Library ads that match, not organic posts. post (id): one public post. profile (profile_id): a page or profile by ID or public handle. profile_posts (profile_id; optional count, cursor): its posts. comments (post_id; optional count, cursor): a post's comments, about 10 per page. post and profile return the item itself. List actions return { results, next_cursor, next }. For the next page, call again with the same action and target and cursor set to next_cursor, unchanged; next_cursor is null on the last page. A cursor lasts 24 hours.

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": {
      "action": "<action>"
    },
    "name": "facebook"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNopost: the public Facebook post or media ID.
tagNohashtag: the hashtag without #, example: 'ai'. A leading # is removed.
countNoMost items to return (1-100). API default: 10 for search, 20 for the other list actions. One page may hold fewer.
queryNosearch: keyword or phrase, example: 'running shoes'.
actionYesWhat to read: 'search', 'post', 'profile', 'profile_posts', 'comments', or 'hashtag'.
cursorNonext_cursor from the previous page of the same action and target, sent back unchanged. Omit it for the first page.
post_idNocomments: the public Facebook post or media ID.
profile_idNoprofile, profile_posts: page or profile ID, or its public handle, example: 'facebook'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/openWorldHint/non-destructive, and the description adds substantial context on top: the ad-library-vs-organic distinction, the ~10-comments-per-page density, the exact return shape {results, next_cursor, next} for list actions vs. the bare item for post/profile, and the 24-hour cursor lifetime. This is behavior an agent could not infer from structured fields alone.

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?

Verb and core purpose are front-loaded, and the action/return breakdown is dense but scannable. There is mild redundancy—'cursor set to next_cursor, unchanged' repeats the schema's 'sent back unchanged'—and the middle section runs as one long sequence, keeping it from a 5.

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, the description carries the full burden of explaining returns and it does: explicit shape for list vs. single-item actions, pagination loop mechanics, terminal-page signaling (next_cursor null), and cursor expiry. An agent can paginate correctly and pick the right action without any external information.

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 100%, so the baseline is 3; the description still earns credit by tying each parameter to the action that consumes it (query→search, tag→hashtag without #, id→post, post_id→comments, profile_id→profile/profile_posts) and by explaining that cursor must be sent back unchanged. It stops short of adding syntax or format detail beyond the schema, so it is not a 5.

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?

Opens with a specific verb and resource ('Read public Facebook data with Desearch') and then enumerates every action (search, hashtag, post, profile, profile_posts, comments) with what each returns. The platform-specific framing plus the exhaustive action list makes it immediately distinguishable from the instagram, tiktok, and x-* siblings without consulting the schema.

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?

Gives clear per-action context and a crucial caveat that search/hashtag return Meta Ad Library ads rather than organic posts, which prevents a whole class of misuse. However, it never states when to choose this tool over the sibling platform tools, and gives no exclusions or prerequisites—selection guidance within the tool is strong, across tools it is absent.

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

All Desearch 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