Skip to main content
Glama
Sign In

Nilyo

by com.nilyo
OverviewDiscussionsAdmin

Facebook / Messenger: Add post reaction

facebook_add_post_reaction
Destructive

React to this post as the explicitly selected identity. External action: preserve explicit user approval. Never retry after an uncertain failure; inspect current state first.

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": {
      "post_id": "<post_id>",
      "reaction": "<reaction>",
      "react_as": "<react_as>"
    },
    "name": "facebook_add_post_reaction"
  }
}

Input Schema

NameRequiredDescriptionDefault
post_idYesFull Facebook post.id (<author_id>_<post_id>) from facebook_list_user_posts or facebook_get_post. Not a URL, text or author ID alone.
react_asYesExplicit publishing identity: me or an activated administered Page ID from facebook_list_inboxes -> page_id, verified in Hosted Auth. A Page's messaging id and profile_id can differ. Never infer one from the other; reconnect the same account to activate Pages.
reactionYes
account_idNoOwned Facebook unipile_account_id from list_connected_accounts. Not a Facebook person or Page ID. Required when several Facebook accounts exist.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already signal destructiveHint=true, idempotentHint=false and openWorldHint=true, so safety is covered. The description adds genuinely non-obvious operational context beyond the structured fields: the reaction must be performed as an explicitly approved identity, and failures must not be retried blindly but state inspected first. It stops short of explaining what a successful reaction returns or how duplicates are handled, keeping it from a 5.

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?

Three short sentences with no padding; the identity constraint is front-loaded and the retry warning follows. Slightly telegraphic ('External action:') but every sentence carries behavioral weight.

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 non-idempotent, destructive external write with no output schema, the description covers the two highest-risk aspects (approval and retry behavior) but omits what success looks like, whether re-reacting overwrites an existing reaction, and permission/scope requirements. Adequate but leaves meaningful gaps for a destructive mutation.

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 75% with strong per-field documentation for post_id and react_as (including the Page messaging ID vs profile_id warning), so the schema does the heavy lifting. The description's only parameter-related contribution is reinforcing the 'explicit identity' requirement, which the react_as schema description already states in more detail. Baseline 3.

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 a specific verb+resource: 'React to this post', and the phrase 'as the explicitly selected identity' scopes it to the react_as parameter. It distinguishes itself implicitly from comment-reaction and removal siblings (add vs remove, post vs comment) but never names an alternative, so no explicit sibling differentiation.

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?

Gives real when-to-use guardrails ('preserve explicit user approval', 'Never retry after an uncertain failure; inspect current state first'), which is more than most definitions. However it never routes the agent to alternatives like facebook_remove_post_reaction or facebook_list_post_reactions, so usage is implied rather than resolvable against siblings.

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

All Nilyo 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