tg-agent

Overview Schema Source Related Servers Discussions Admin

Plan download

tg_plan_download

Read-only

Preview a Telegram download before running it: see file count, total size, split-archive gaps, already-downloaded files, approval needs, and estimated duration without queuing anything.

Instructions

Dry run of tg_download with the same arguments: how many files, total size, split-archive sets (and missing volumes), files already downloaded elsewhere, whether approval will be needed, and an estimated duration. Nothing is queued. Use it before large downloads.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "tg_plan_download"
  }
}

Input Schema

Name	Required	Description	Default
`chat`	No	Chat: @username, username, t.me link, t.me/c/<id> link, or numeric id such as -100123…
`limit`	No
`links`	No
`since`	No	Start date, ISO (e.g. 2025-01-01).
`types`	No	File kinds. Default: everything except stickers.
`until`	No	End date, ISO.
`fields`	No	Keep only these fields in list items (e.g. ["message_id","name","size"])
`format`	No	compact = lists as {columns, rows} tables; saves a lot of context for long listings	json
`account`	No	Account id (see tg_list_accounts). Defaults to the default account.
`extensions`	No	Extensions, e.g. ["zip", "mp4"].
`max_size_mb`	No
`message_ids`	No
`min_size_mb`	No
`oldest_first`	No
`include_album`	No
`name_contains`	No	File name or caption contains (case-insensitive).
`complete_archives`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds real substance beyond them: "Nothing is queued" confirms no side effects, and it discloses the returned payload, including the non-obvious predictions (missing archive volumes, files already downloaded elsewhere, whether approval will be needed, estimated duration). With no output schema, this is the only place that information exists.

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?

Two sentences: the first defines the tool and front-loads the output inventory, the second states the no-side-effect guarantee and the usage trigger. Every clause carries information; nothing is redundant with the title or annotations.

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?

For a 17-parameter, annotation-covered read-only tool with no output schema, the description covers purpose, side effects, return contents, and usage timing. Minor gaps remain: it does not say how limit/filters affect the estimate's accuracy or whether the plan can be fed directly into tg_download, but nothing essential to calling it correctly is missing.

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?

The description adds no per-parameter meaning; it only asserts the arguments are the same as tg_download, which is a useful pointer but not semantics. Schema coverage is 53%, with the ambiguous filters (chat, since, types, format, fields, account, name_contains) documented in the schema while the remaining numeric/boolean filters are largely self-explanatory, so the moderate baseline of 3 fits.

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?

Names a specific operation (dry run of tg_download with identical arguments) and enumerates exactly what it produces: file count, total size, split-archive sets and missing volumes, already-downloaded files, approval requirement, and estimated duration. It explicitly frames itself against the sibling tg_download, so an agent can pick the right one without opening a schema.

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?

"Use it before large downloads" gives a clear trigger condition, and the framing as a dry run of tg_download makes the alternative obvious. It does not state an explicit when-not (e.g. small downloads where the estimate is not worth a call), so it stops short of full routing guidance.

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