Skip to main content
Glama

reply_to_inbox

Destructive

Reply to an existing inbox conversation (DM, comment, or mention) on Instagram, Facebook, LinkedIn, TikTok, YouTube, X, or Threads. You can only reply to conversations that already exist. For a comment or mention, pass message_id (the #id of the comment being answered): comments on one post share a conversation and without it the reply goes under the newest comment on the post. Meta direct-message replies must be within the platform's 24-hour messaging window: a 422 outside_messaging_window means the window has closed, nothing was sent, and the user must answer that DM from the Instagram or Facebook app (mirrored into the inbox) or skip it with mark_inbox_read; do not retry. TikTok replies are comments only, text-only, and capped at 150 characters; they can take a few minutes to appear on TikTok while they pass spam review. YouTube replies are comments only. Threads replies are on the workspace's posts and mentions; a 401 reauth_required means the Threads connection must be reconnected to grant the reply permission. X replies are DM-only and use credits from the organisation's existing balance (X's API fee passed through); a 402 insufficient_credits error means that balance is too low — tell the user and do not retry. attachment_url/attachment_type let you send media on a Facebook or Instagram DM (text is optional when an attachment is set); other platforms are text-only. Set include_next: true to get the next conversation that needs an answer back in the same call (same as get_next_unanswered), so the inbox can be worked through as: get_next_unanswered → draft → reply_to_inbox(include_next) → draft → repeat. A 409 duplicate_reply means this exact reply already went out to this conversation in the last 10 minutes (an earlier call that looked slow or failed did succeed) or is being sent right now: nothing was sent again, do NOT retry it — continue with get_next_unanswered. A 422 reply_not_allowed means the platform refuses replies to this item for good (Facebook #1705: the comment sits on a share or boosted copy of the post, or the commenter restricts replies; YouTube: the thread's canReply is false because comments are off on the video or the comment was removed or held for review): the item is dropped from get_next_unanswered automatically, tell the user, and do NOT retry.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNoThe reply text (max 2000 characters; TikTok comments max 150). Optional when attachment_url is set.
message_idNoFor comment/mention threads: the inbox id of the comment you are answering (the 'Message to answer' #id from get_next_unanswered, or a #id from get_inbox_conversation). Every comment on a post shares one conversation, so without it the reply is posted under the newest comment on the post, which can be a different person than the one you drafted for. Always pass it for comments. Ignored for DMs.
include_nextNoAfter sending, also return the next conversation that needs an answer (full thread + post context), or 'nothing waiting'
attachment_urlNoMedia URL to send (Facebook and Instagram DMs only)
attachment_typeNoimage, video, audio, or file — required if attachment_url is set
conversation_idYesThe conversation ID to reply to

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare destructiveHint=true, openWorldHint=true, readOnlyHint=false, and the description adds platform-specific behavior far beyond them: the Meta 24-hour messaging window, TikTok 150-character text-only limit and spam-review delay, YouTube canReply restrictions, X credit-based billing, and the exact semantics of 409 duplicate_reply and 422 reply_not_allowed. This is the kind of disclosure an agent needs to avoid retry loops and misrouted replies.

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 content is valuable but presented as a single dense paragraph with no line breaks or grouping by platform/error code, making it harder to scan than necessary. The first sentence is well front-loaded, but the remainder is a wall of run-on error and platform detail that could be structured into bullets without losing information.

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?

For a complex, multi-platform mutation tool with no output schema, the description covers success behavior, platform-specific constraints, all important error codes and their required next actions, and the include_next return contract. An agent has everything needed to call this correctly and recover from failures.

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 description coverage is 100%, so the baseline is 3, but the description meaningfully enriches parameter usage by explaining why message_id must always be passed for comments (conversation sharing on a post) and how include_next chains into the inbox workflow. It also restates attachment constraints and platform-specific text limits that the schema only partially captures.

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?

The first sentence states a specific verb (reply) and resource (existing inbox conversation) and enumerates the exact platforms covered. It distinguishes itself from siblings like get_next_unanswered and get_inbox_conversation by requiring an already-existing conversation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance, names alternative tools for adjacent actions (mark_inbox_read, get_next_unanswered), and details the exact error-specific routing for 422, 409, 401 and 402 cases, including when not to retry. The get_next_unanswered → draft → reply_to_inbox(include_next) workflow is spelled out step by step.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources