StealAds

Get an ad

get_ad

Read-onlyIdempotent

Returns the details of one ad by id, from this account or the public Ad Library: caption, headline, call to action, media URLs, run dates, delivery evidence, strength label and hook (hook.spoken is a video's opening line, hook.on_screen its opening overlay text). For reading one ad closely before saving or adapting it. Full video transcripts are left out. The detail is JSON in both text and json formats.

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": {
      "ad_id": "<ad_id>"
    },
    "name": "get_ad"
  }
}

Input Schema

Name	Required	Description
`ad_id`	Yes	Ad id from a search or list result: the row's id, or in text results the final segment of its StealAds ad link.
`analysis_detail`	No	How much stored analysis to include for ads in this account (default none). Public Ad Library ads return their standard fields either way.
`response_format`	No	Output format: text (default) is readable text with image previews and links; json returns the structured rows. table is refused by Ad Library tools.

Output Schema

Name	Required	Description	Default
`ad`	No	ad value in this response.
`source`	No	Where the accessible ad or advertiser evidence came from.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 10, 2026

changedInput schema / properties / ad_id / description

Previous value: -"Ad id from search_ads or from your competitors' ads."New value: +"Ad id from a search or list result: the row's id, or in text results the final segment of its StealAds ad link."

changedInput schema / properties / analysis_detail / description

Previous value: -"How much of the ad analysis to include for your own ads (default none)."New value: +"How much stored analysis to include for ads in this account (default none). Public Ad Library ads return their standard fields either way."

changedInput schema / properties / response_format / description

Previous value: -"Response format. Defaults to readable text; json returns the closed public data contract. Library tools refuse table; use text or json."New value: +"Output format: text (default) is readable text with image previews and links; json returns the structured rows. table is refused by Ad Library tools."

First observedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already establish read-only, idempotent, closed-world behavior, and the description adds real value beyond them: the exact field set returned, the meaning of hook.spoken vs hook.on_screen, and the explicit limitation that "Full video transcripts are left out." The closing line about JSON in both text and json formats is muddled against the schema's stated text/table options, keeping it from a 5.

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 purpose and scope are front-loaded in the first sentence, and the parenthetical hook definition is efficiently packed. The final sentence about JSON formats is both unnecessary given the output schema and slightly confusing, costing a point.

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 single-record read with a full output schema and complete annotation coverage, the description covers scope, use case, exclusions, and notable field semantics. The only gap is the ambiguous statement about output formats, which an agent may have to reconcile with the 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 ad_id, analysis_detail, and response_format are already documented with enums and defaults. The description adds no parameter-level detail (e.g., what analysis_detail levels yield), so baseline 3 applies; the hook explanation clarifies returned fields, not inputs.

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 definition opens with a specific verb and resource ("Returns the details of one ad by id") and then enumerates the payload (caption, headline, CTA, media URLs, run dates, delivery evidence, strength label, hook), so an agent knows exactly what it gets. It also scopes the source ("this account or the public Ad Library"), distinguishing it from list/search siblings.

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?

It gives an explicit use case: "For reading one ad closely before saving or adapting it," which tells the agent when this is preferred over search or gallery tools. It does not explicitly name an alternative (e.g., show_ad_gallery or find_winning_ads) or state when not to use it, so it falls short of a 5.

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

All StealAds tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.