Skip to main content
Glama

Local MCP

by com.local-mcp
OverviewDiscussionsAdmin

Telegram Send Message

telegram_send_message
Destructive

Sends a Telegram message from your own account to one chat. WRITE operation with a preview: the first call (confirm=false) returns a preview and sends NOTHING; show it to the user and call again with confirm=true only after they approve. The preview names the recipient from Telegram itself (chat_name is Telegram's name for chat_id; chat_name_unresolved when the id is not among the account's recent chats, or when reading that account is turned off in its row of My apps), never from what the caller passed. chat_id MUST come from telegram_list_chats — never invent one. One message per call; no bulk sending.

Input Schema

NameRequiredDescriptionDefault
accountNoWhich linked Telegram account to use: its label or id from telegram_list_accounts. Leave it out to use the default account.
chat_idYesChat id from telegram_list_chats.
confirmNoMust be true to actually send. Without it, returns a preview.
messageYesText to send (max 4096 characters).
rememberNoWith confirm: true, also stop asking for this kind of action from now on. Only when the person said so ("don't ask again"). The person can revoke it in LMCP or with set_always_allowed.
chat_nameNoOptional: the name you expect for chat_id. It is never shown as the recipient — the preview shows Telegram's own name for chat_id and sets chat_name_mismatch when yours differs.
reply_to_message_idNoOptional: the id of a message in this chat (from telegram_read_messages) that this message replies to. To acknowledge a message for telegram_delete_message, reply to it with the text ACK.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / remember
      Added value: +{
+  "description": "With confirm: true, also stop asking for this kind of action from now on. Only when the person said so (\"don't ask again\"). The person can revoke it in LMCP or with set_always_allowed.",
+  "type": "boolean"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / chat_name / description
      Previous value: -"The chat's name as telegram_list_chats showed it, echoed in the preview so the user sees who receives it."New value: +"Optional: the name you expect for chat_id. It is never shown as the recipient — the preview shows Telegram's own name for chat_id and sets chat_name_mismatch when yours differs."
    • addedInput schema / properties / reply_to_message_id
      Added value: +{
+  "description": "Optional: the id of a message in this chat (from telegram_read_messages) that this message replies to. To acknowledge a message for telegram_delete_message, reply to it with the text ACK.",
+  "type": "integer"
+}
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only flag it as a non-read-only, destructive, open-world write; the description adds the real behavioral contract: a preview phase that sends nothing, the second confirm call that actually sends, who supplies the recipient name (Telegram, not the caller), and the chat_name_mismatch/chat_name_unresolved signaling. This is exactly the kind of side-effect and safety detail annotations cannot express.

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-loaded with the verb and the WRITE-with-preview warning, and every sentence carries operational information. It is dense and parenthetical-heavy in the recipient-name explanation, which makes it slower to parse than it needs to be, but nothing is expendable.

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 7-parameter write tool with full schema coverage, an output schema, and safety annotations, the description covers the confirmation workflow, the dependency chain (list_chats -> send), recipient-name resolution edge cases, and the no-bulk constraint. Nothing needed to invoke it correctly is missing.

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 3 baseline is already met, and the description goes beyond it by explaining chat_name's semantics (expected name only, never displayed as recipient, triggers mismatch flag) and the provenance constraint on chat_id. It does not elaborate message length limits or reply_to_message_id, but those remain documented in the schema, so the incremental value is real but partial.

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 and resource ('Sends a Telegram message from your own account to one chat') plus the scope limit ('One message per call; no bulk sending'). The Telegram platform prefix plus the explicit single-chat scope distinguishes it from whatsapp_send_message, teams_send_message, and telegram_read_messages without opening another schema.

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 sequencing rules an agent must follow: first call with confirm=false sends nothing, show the preview, re-call with confirm=true only after user approval. It also states a hard prerequisite ('chat_id MUST come from telegram_list_chats — never invent one') and an exclusion ('no bulk sending'), leaving no inference required.

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

All Local MCP 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