Skip to main content
Glama

max_check_ad_post

Read-onlyIdempotent

Checks a MAX ad post for Russian ad-marking rules: Реклама label, advertiser details, erid, A+ mark for 10k+ channels, and 4,000-character limit; returns hints, not legal advice.

Instructions

Check an ad post for MAX against Russian ad marking rules: the 'Реклама' label at the top, advertiser details (name and INN/OGRN or a site), an erid token in the link or text, the A+ mark for channels over 10,000 subscribers, and the 4000-character limit. A hint, not legal advice; ORD registration is not checked.

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": {
      "text": "<text>"
    },
    "name": "max_check_ad_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoAnswer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
textYesAd post text as it will be published
linksNoLinks used in buttons or elsewhere, if not in the text
advertiser_siteNoSite with the advertiser's details, if they are not in the text
channel_has_a_plusNoWhether the channel has the A+ mark (RKN registry)
channel_subscribersNoSubscribers of the channel where it goes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add limitation context, which it does: 'A hint, not legal advice' and 'ORD registration is not checked' tell the agent how much to trust and where the check stops. It does not describe the shape of the result (pass/fail vs. list of findings), which is the main remaining behavioral gap.

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?

Front-loaded with the verb and resource, then a tight enumerated list where each clause corresponds to one concrete rule check. The closing caveat is two short clauses that both carry real scope information; nothing is redundant with the title or schema.

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?

With six parameters, full schema coverage, and no output schema, the description covers the input side well and states the domain and its limits. The notable omission is return-value behavior: an agent cannot tell from the description whether it receives a boolean verdict, a list of violations, or per-rule findings, which matters for a checker with no output schema.

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?

Schema description coverage is 100%, so the schema already documents every parameter, making 3 the baseline. The description does add some linkage — the A+ rule's 10,000-subscriber threshold connects channel_has_a_plus to channel_subscribers, and the erid/link and advertiser-site rules map to links and advertiser_site — but it never explains these mappings explicitly enough to exceed the baseline by much.

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 description opens with a specific verb and resource ('Check an ad post') and enumerates exactly what is verified: the 'Реклама' label, advertiser name/INN/OGRN or site, erid token, A+ mark, and the 4000-character limit. That is far more concrete than a generic 'validate' tool. It stops short of naming or contrasting a sibling (e.g. max_ad_report), so the boundary with the reporting tool is left implicit.

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?

Usage is only implied: the agent can infer the tool is for pre-publication review of a MAX ad post. The one explicit exclusion, 'ORD registration is not checked', is genuinely useful, but there is no statement of when to prefer this over max_ad_report or other validation siblings, and no prerequisites are given.

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