Skip to main content
Glama

radar_ads

Read-onlyIdempotent

Find the ads a competitor (or any search term) is running, from the ad libraries Hookbird is connected to (cached 24 hours). Free. Each ad has its hook text, platform, how many days it has been running (long-running ads are the ones that make money) and a short why. "providers" says which sources are on and, when one is off, why. When "ads" is empty and no provider is enabled, tell the user ad sources are not set up, do not invent ads. When "note" is set, no source covers the asked market: say so and that the ads shown ran elsewhere (each ad's "country"). Competitor names are in brand_profile. Use winning hooks as inspiration for hooks_generate (topic: "remix: ..."). Each ad says whether it is the competitor's own ("own": its advertiser carries the competitor's name and, when brand_profile lists the competitor's site, its ads land there) or only mentions the search word (another advertiser), and whether its text is a template ("templated": a dynamic ad whose words are filled per viewer, like "{{product.brand}}", so they are not public). Only cite, compare or remix the competitor's own ads with real text; say plainly when there are none.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "radar_ads"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoOr a free search term
limitNoHow many ads (default 10)
countryNoTwo letter country code (default: the brand’s market)
minDaysNoOnly ads running at least this many days
activeOnlyNoOnly ads still running
competitorNoCompetitor brand name, e.g. "Wafeq"

Output Schema

NameRequiredDescriptionDefault
adsNo
noteNo
errorNo
queryNo
totalNo
marketNo
providersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / market
      Added value: +{
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedOutput schema / properties / note
      Added value: +{
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent, but the description adds a lot beyond them: results are cached 24 hours, the call is free, results may be empty or carry a 'note' when no source covers the market, and each ad carries provenance ('own') and template-status ('templated') flags. It even states the interpretation rule ('only cite, compare or remix the competitor's own ads with real text'). This is substantial behavioral context annotations cannot provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and constraints are front-loaded, which is good, but the block is long and dense, and several sentences restate output-schema fields ('providers' says which sources are on, each ad's 'country', 'own', 'templated') even though an output schema exists. The edge-case guidance earns its place; the field-by-field restatement does not fully.

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

Completeness5/5

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

For a tool with multiple failure modes (no providers enabled, no coverage for the market, foreign-country results, templated text, non-competitor advertisers), the description covers every case the agent must handle to answer correctly. Nothing needed to invoke or interpret the result is missing.

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 coverage is 100%, so the baseline is 3; the description adds meaning by framing competitor and q as alternatives ('a competitor (or any search term)') and by tying country to the brand's market and to per-ad 'country' values. limit, minDays and activeOnly are left entirely to the schema, so it is an incremental rather than complete addition.

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?

States a specific verb and resource ('Find the ads a competitor ... is running, from the ad libraries Hookbird is connected to'), plus the scope ('competitor or any search term') and freshness ('cached 24 hours'). An agent can distinguish this from radar_trends or hooks_generate without opening any schema.

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?

Gives explicit routing: competitor names come from brand_profile, and winning hooks should feed hooks_generate with a 'remix: ...' topic. It also prescribes behavior for the empty/no-provider case ('tell the user ad sources are not set up, do not invent ads'). It stops short of excluding use versus other research siblings like radar_trends, so not a full 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources