Skip to main content
Glama
Sign In
tg-agent

tg-agent

by Creatfire
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Start workflow

tg_start_workflow
Read-only

Start a new tracked workflow before any other tg_* tool so every Telegram request is grouped, inspectable, and closes the previous session.

Instructions

Call this FIRST for every new user request, before any other tg_* tool, with a short title describing the request (in the user's language). The user watches your calls grouped under this workflow in the TG Agent console. Starting a new workflow closes the previous one.

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": {
      "title": "<title>"
    },
    "name": "tg_start_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNoOptional: what the user asked for, in one or two sentences
titleYesShort title, e.g. 'Download new videos from @telegram'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

The annotations already state readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds context the annotations lack, namely that the user sees the calls grouped in the TG Agent console and that starting a new workflow closes the previous one. That side effect is exactly the kind of behavior an agent needs to know before calling it casually, though it sits in mild tension with readOnlyHint and could have said so more plainly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, with the most important instruction ('Call this FIRST') front-loaded. The ordering rule, the visible grouping, and the closing side effect each earn their place, with no redundancy against the schema.

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 two-parameter call-tracking tool with no output schema and annotations covering safety, the description covers everything needed: when to call it, what to put in the title, and the side effect of starting a new one. Nothing an agent needs in order to call 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 both parameters are documented; the description still adds meaning by specifying that the title should be short and in the user's language, which is not in the schema. The optional 'goal' parameter is left entirely to its schema description, but that only slightly limits the added value.

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 description names a specific action (start a workflow) with a precise scope: it must be the first call for every new user request, ahead of any other tg_* tool. That framing tells an agent exactly which step this is in a session, distinct from the sibling tools that do the actual work.

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

Usage Guidelines4/5

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

It gives a clear, unconditional when-to-use rule ('Call this FIRST for every new user request, before any other tg_* tool') and a when-to-be-careful warning ('Starting a new workflow closes the previous one'). It does not name tg_finish_workflow as the explicit counterpart for ending a session, but the ordering condition is unambiguous.

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

Deploy Server

Other Tools