telegram-ads-mcp

Overview Schema Source Related Servers Discussions Admin

create_ad

Create an ad for Telegram Ads campaigns with targeting by channel, bot, search, or user, and configure budget, schedule, and audience to launch campaigns.

Instructions

Create an ad. TON/Gram cabinets allow channels, bots, search, and users (geo). EUR too.

Always create on_hold. Budget "0" cannot go to review. IDs are semicolon-separated.
Search ads: do not pass text/picture/media.
Empty strings are stripped and not sent.
Do not send langs together with specific channel IDs (platform Target invalid) —
langs is dropped in that case.
confirm: required for spend (budget>0 or active) when TG_ADS_WRITE_GATE is not open.

Input Schema

TableJSON Schema

Name	Required	Default
`cpm`	Yes
`bots`	No
`text`	No
`langs`	No
`media`	No
`title`	Yes
`active`	No	on_hold
`budget`	No	0
`button`	No
`device`	No
`topics`	No
`confirm`	No
`picture`	No
`channels`	No
`schedule`	No
`countries`	No
`locations`	No
`user_langs`	No
`audience_id`	No
`only_crypto`	No
`promote_url`	Yes
`schedule_tz`	No
`target_type`	No	channels
`user_topics`	No
`daily_budget`	No	0
`only_politic`	No
`website_name`	No
`activate_date`	No
`user_channels`	No
`exclude_crypto`	No
`exclude_topics`	No
`search_queries`	No
`views_per_user`	No	1
`deactivate_date`	No
`exclude_politic`	No
`conversion_event`	No
`exclude_channels`	No
`intersect_topics`	No
`schedule_tz_custom`	No
`exclude_user_topics`	No
`exclude_user_channels`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 30, 2026

addedInput schema / properties / confirm

Added value: +{
+  "default": false,
+  "title": "Confirm",
+  "type": "boolean"
+}

First observedv0.2.0Aug 29, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Discloses several non-obvious behaviors beyond the annotations: enforced on_hold status, zero-budget ads not going to review, empty strings being stripped and not sent, langs being dropped on conflict, and the confirm gate for spending. These are exactly the side effects and constraints an agent needs, and none contradict the annotations.

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?

The description is dense and front-loaded, with each sentence covering a distinct operational rule. The phrasing 'TON/Gram cabinets' and 'EUR too' is somewhat cryptic, but the overall size is appropriate for the tool's complexity.

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

Completeness3/5

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

The critical safety, validation, and spending constraints are present, and the output schema covers return expectations. Still, for a 41-parameter creation tool, significant details around target_type-specific fields, scheduling, and targeting exclusions are left implicit.

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 useful cross-cutting parameter semantics such as semicolon-separated IDs, empty-string stripping, search-ad exclusions (text/picture/media), the langs/channels conflict, and the confirm requirement. However, with 41 parameters and 0% schema description coverage, many parameters like cpm, schedule, targeting options, and conversion_event still rely on self-explanatory names rather than documented meaning.

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 opens with 'Create an ad'—a clear verb-and-resource statement that distinguishes it from sibling tools like edit_ad, delete_ad, and clone_ad. The additional context about target types and supported cabinets does not obscure the core purpose.

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?

The description provides explicit when-to/when-not-to rules: always create on_hold, do not pass text/picture/media for search ads, do not combine langs with channel IDs, and confirm is required for spend when the write gate is closed. It does not explicitly name alternative tools, but the primary use case is clear from the name and sibling set.

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