Skip to main content
Glama
telegram-channels-mcp

telegram-channels-mcp

reply_comment

Destructive

Post a public comment on your own Telegram channel post or reply to a specific comment; requires a preview and confirm token before anything is sent.

Instructions

Write a comment under a post of the user's own channel, or reply to a specific comment there (comment_id from get_comments). The reply is sent from the user's account. DANGEROUS: it is public. Without confirm_token nothing is sent: you get a preview and a confirm_token. Show the preview to the user and repeat the call with the same arguments and confirm_token ONLY after the user explicitly approves this exact text

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": {
      "channel": "<channel>",
      "post_id": "<post_id>",
      "text": "<text>"
    },
    "name": "reply_comment"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
channelYes
post_idYes
comment_idNo
confirm_tokenNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructive=true, openWorld=true, and non-idempotent, and the description adds real substance beyond them: the action is public, it is attributed to the user's account, and crucially it is dry-run by default — nothing is sent without confirm_token. That dry-run semantics is not expressible in the annotations and is the key behavioral fact. It does not cover irreversibility (can the comment be deleted?) or rate limits, so not 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?

Front-loads what the tool does, then the danger warning, then the confirm protocol in execution order — a logical sequence an agent can follow. Every sentence is load-bearing, though the final sentence runs long by chaining the approval condition and the 'exact text' requirement together, which slightly blunts the most safety-critical instruction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is not needed, and the confirm_token preview cycle is described well enough to drive the interaction. The remaining gap is parameter-level: an agent still has no guidance on channel format or text constraints, which matters for a public, destructive write against a 0%-described schema.

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 description coverage is 0%, so the description carries the burden and does so only partially. It explains comment_id's provenance (from get_comments) and its role in choosing reply vs. top-level, and it fully defines confirm_token's two-phase behavior. However channel, post_id, and text are undocumented — the closest it comes is implying channel is the user's own, with no format for the identifier and no constraints on text length or content.

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?

States a specific verb (write/reply) and resource (comment under a post), plus the exact scope restriction: only the user's own channel. The two modes — top-level comment vs. reply via comment_id — are distinguished within the same sentence, so an agent knows exactly what the tool does versus publish_post or get_comments.

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?

Gives explicit routing ('comment_id from get_comments'), the prerequisite (user's own channel), and a precise two-step call protocol: first call without confirm_token to get a preview, second call with the token only after explicit user approval of that exact text. It also names the condition that gates execution, which is rare specificity.

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