tg-agent

Overview Schema Source Related Servers Discussions Admin

Watch chats

tg_watch

Create and manage watches that automatically download new matching files from Telegram chats, with user approval required before a watch runs. List, pause, resume, or check watches as needed.

Instructions

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": "tg_watch"
  }
}

Input Schema

Name	Required	Description
`chat`	No	Chat: @username, username, t.me link, t.me/c/<id> link, or numeric id such as -100123…
`types`	No	File kinds. Default: everything except stickers.
`action`	Yes
`subdir`	No
`account`	No	Account id (see tg_list_accounts). Defaults to the default account.
`watch_id`	No
`extensions`	No	Extensions, e.g. ["zip", "mp4"].
`max_size_mb`	No
`min_size_mb`	No
`interval_min`	No
`name_contains`	No	File name or caption contains (case-insensitive).
`include_recent`	No	On add: also consider the last N messages

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

B3.1/5.0

Behavior3/5

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

The description adds one genuinely non-obvious behavioral fact not in the annotations: newly added watches stay disabled until the user approves them in the console, which affects how the agent should report results back. Beyond that it stays silent on the semantics of 'check' (does it trigger a run or just report status), whether 'remove' is reversible, and what 'matching' means when filters are omitted. Annotations cover safety (destructiveHint=false, openWorldHint=true), so this is a moderate rather than severe gap.

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?

Two tight sentences: the purpose leads, the action enum follows compactly, and the approval constraint closes. No filler, though the action enum could be formatted more readably and the approval sentence could be merged more tightly with guidance on how to respond to the user.

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

Completeness2/5

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

This is a 12-parameter, multi-action mutating tool with no output schema, and the description does not say what 'list' returns, what an auto-downloaded file becomes (indexed? visible via tg_list_files?), or what 'check' produces. For a tool of this complexity the definition is under-specified even though its safety profile is covered by annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 12 parameters and only 50% schema description coverage, the description carries a real burden and provides almost nothing: it never mentions chat resolution, type/extension/size filters, interval_min, subdir, watch_id, include_recent, or the account selector. The phrase 'matching files' gestures at filters but gives no meaning or combination rules for them.

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 and resource ('Manage watches that automatically download new matching files from a chat') and enumerates the action vocabulary, so the agent knows this is about persistent auto-download rules rather than one-off fetches. It does not explicitly name a sibling such as tg_download or tg_plan_download to contrast with, which keeps it short of a 5.

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?

The action list implies usage modes (list/add/remove/pause/resume/check), and the approval note tells the agent an added watch is not live immediately. However, there is no guidance on when to use this instead of tg_download/tg_plan_download, no prerequisites for 'check', and no statement of what happens if you pause or remove a watch that is mid-download.

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