Inside Ads

estimate_campaign

Estimate reach, clicks and cost of advertising a product to Telegram audiences — no account or authorization required. Call this FIRST, before asking the user to connect an account: it tells you whether inside.ad has relevant inventory for this product and what a given budget would buy. Describe the product yourself (you know it better than any crawler); the URL alone is a weak signal.

Input Schema

TableJSON Schema

Name	Required	Description
`geo`	No	Optional ISO-2 country filter, e.g. "US"
`url`	No	Product landing page URL
`lang`	No	Optional audience language filter, e.g. "en"
`budget`	No	Budget in USD to estimate against (default 100)
`keywords`	No	Optional topic keywords, e.g. ["devtool","ai"]
`description`	No	What the product does, in your own words. Strongest signal for topic matching.

Output Schema

TableJSON Schema

Name	Required	Description
`budget`	Yes	Budget the estimate was computed for, in USD
`cpmUsd`	No	Reach-weighted average CPM across matched segments
`cpcRange`	No	Implied cost per click in USD, derived from CPM and the CTR band.
`currency`	Yes
`dailyReach`	No	Total daily impressions available in matched segments
`assumptions`	No
`deliveryDays`	No	Roughly how many days it takes to deliver estimatedImpressions at the current daily reach.
`sampleSegments`	No	Matched inventory segments. Individual channels are deliberately not disclosed.
`estimatedClicks`	Yes	Range, not a point estimate. Report both ends to the user.
`inventoryIsThin`	Yes	true = there is no matching inventory at all, OR the budget exceeds what the matched inventory can deliver. Say so plainly instead of promising results, and use spendableBudget as the realistic figure.
`spendableBudget`	No	How much of the budget this inventory can actually absorb within 30 days. If it is lower than budget, tell the user to either lower the budget or widen targeting — do not promise the full budget will be spent.
`matchedCategories`	No
`estimatedImpressions`	Yes

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations provided, the description correctly states that no account or authorization is required, which is critical behavioral context. It implies the tool is a read-only estimation (no side effects mentioned), but could explicitly state idempotency or that it does not create any resource. The presence of an output schema partially covers return values, but the description could be slightly more explicit about safety.

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 concise sentences each serve a distinct purpose: defining the tool, specifying when to call it and what it returns, and offering practical advice. No redundant or wasted content; every sentence is essential and front-loaded with key information.

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?

Given the tool's complexity (6 optional parameters, output schema present, sibling tools), the description covers core purpose, usage order, and a critical parameter hint. It does not detail error scenarios or behavior when filters yield no results, but the output schema likely covers the return structure. Overall, it provides sufficient context for effective selection and invocation.

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 description coverage is 100%, so each parameter is already documented. The description adds meaning by emphasizing the 'description' parameter as the strongest signal and warning that 'the URL alone is a weak signal', which guides proper usage. This extra context raises the value above the baseline of 3.

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 explicitly states the tool estimates 'reach, clicks and cost' for 'advertising a product to Telegram audiences', using specific verbs and a clear resource. It distinguishes itself from siblings by positioning it as the first step before account connection, effectively differentiating from create_campaign_draft and get_draft_status.

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

Usage Guidelines5/5

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

Explicit guidance is provided: 'Call this FIRST, before asking the user to connect an account'. It explains what the tool tells you (inventory relevance and budget capabilities) and advises on best practice ('Describe the product yourself...the URL alone is a weak signal'), leaving no ambiguity about when and how to use it.

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

All Inside Ads tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0

Disambiguation5/5

Each tool targets a distinct phase of the campaign workflow: estimate_campaign for initial feasibility, create_campaign_draft for generating the draft, and get_draft_status for tracking progress. There is no overlap in purpose.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (estimate_campaign, create_campaign_draft, get_draft_status), making the action and object immediately clear.

Tool Count5/5

Three tools is appropriately scoped for the service: a pre-flight estimate, a creation step, and a status check. No tool feels redundant or missing for the agent's role.

Completeness4/5

The tools cover the core workflow (estimate → create → check status) completely for the agent's interaction. The only minor gap is lacking a way to modify or cancel a draft before the user acts, but the designed flow is linear and doesn't require it.

Resources

Need Help?