Skip to main content
Glama
zai-one

telegram-ads-mcp

by zai-one

create_ad

Create a Telegram ad campaign targeting channels, bots, search, or users with specified budget, schedule, and audience settings.

Instructions

Create an ad. 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cpmYes
botsNo
textNo
langsNo
mediaNo
titleYes
activeNoon_hold
budgetNo0
buttonNo
deviceNo
topicsNo
pictureNo
channelsNo
scheduleNo
countriesNo
locationsNo
user_langsNo
audience_idNo
only_cryptoNo
promote_urlYes
schedule_tzNo
target_typeNochannels
user_topicsNo
daily_budgetNo0
only_politicNo
website_nameNo
activate_dateNo
user_channelsNo
exclude_cryptoNo
exclude_topicsNo
search_queriesNo
views_per_userNo1
deactivate_dateNo
exclude_politicNo
conversion_eventNo
exclude_channelsNo
intersect_topicsNo
schedule_tz_customNo
exclude_user_topicsNo
exclude_user_channelsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

Beyond the annotations' write flag, the description discloses critical runtime behavior: ads are always created in on_hold state, budget 0 blocks review, ID lists are semicolon-separated, search ads must omit text/picture/media, and empty strings are stripped. These are exactly the non-obvious behaviors an agent needs before calling.

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 compact and front-loaded with the main verb, followed by terse constraints. The 'EUR too' fragment is ambiguous and slightly disorganized, but overall every line adds a distinct operational fact with little waste.

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 40-parameter write operation, the description covers the most likely failure points: initial state, budget/review condition, ID format, search-ad parameter restrictions, and empty-string handling. It does not spell out the account/session prerequisite or all target-type parameter relationships, but the output schema and sibling tools compensate.

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?

With 0% schema description coverage, the description provides crucial semantics: semicolon-separated IDs, the search-ad exclusion of text/picture/media, and the budget 0 review rule. It does not define every parameter, but it adds meaning that could not be inferred from the schema alone.

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?

The opening 'Create an ad' states a clear verb and resource, and the surrounding notes (Gram cabinets, target types, search ads) tell the agent this is for a specific advertising domain. It does not explicitly contrast itself with sibling tools like clone_ad or edit_ad, so it stops short of full differentiation.

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 description implies this is the entry point for creating new ads and carries important workflow rules: ads are always created on_hold and a zero budget prevents review. However, it never explicitly says when to prefer create_ad over clone_ad/edit_ad or mentions prerequisites such as an active session/account.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zai-one/telegram-ads-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server