Skip to main content
Glama
Sign In

AdvertiserLeads

by com.advertiserleads
OverviewDiscussionsAdmin

Search ad signals

search_signals
Idempotent

US ecommerce brands flagged on the latest day for a change in their Meta (Facebook/Instagram) ads: newly advertising, scaling, struggling or stopped, with store platform, live ad count and other ad channels. Defaults to new and scaling brands in every niche the caller's plan covers. Without signing in or on the free plan, brand names and domains are masked and only the niche filter applies; each masked row has a ref that reveal_brand unmasks with one of the free plan's monthly reveals. On paid plans each brand returned counts toward the account's monthly export rows (the same brand again that month is free).

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": "search_signals"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoBrand name or domain contains this text. Not on the Free plan.
limitNoRows to return, default 25. Masked results return at most 50.
nicheNoOne niche; all of the caller's niches when left out. An account that hasn't picked a niche yet must pass one, and it becomes the account's niche.
pixelNoAlso advertises on this channel (tracking pixel on the store). Not on the Free plan.
offsetNoRows to skip, for paging.
signalNoOne signal type; newly_advertising and scaling when left out. Not on the Free plan.
min_adsNoAt least this many live ads. Not on the Free plan.
platformNoStore platform. Not on the Free plan.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / min_ads / description
      Previous value: -"At least this many live ads. Paid plans only."New value: +"At least this many live ads. Not on the Free plan."
    • changedInput schema / properties / pixel / description
      Previous value: -"Also advertises on this channel (tracking pixel on the store). Paid plans only."New value: +"Also advertises on this channel (tracking pixel on the store). Not on the Free plan."
    • changedInput schema / properties / platform / description
      Previous value: -"Store platform. Paid plans only."New value: +"Store platform. Not on the Free plan."
    • changedInput schema / properties / q / description
      Previous value: -"Brand name or domain contains this text. Paid plans only."New value: +"Brand name or domain contains this text. Not on the Free plan."
    • changedInput schema / properties / signal / description
      Previous value: -"One signal type; newly_advertising and scaling when left out. Paid plans only."New value: +"One signal type; newly_advertising and scaling when left out. Not on the Free plan."
  2. Changed2 schema fields changed
    • changedInput schema / properties / niche / description
      Previous value: -"One niche; all of the caller's niches when left out."New value: +"One niche; all of the caller's niches when left out. An account that hasn't picked a niche yet must pass one, and it becomes the account's niche."
    • changedInput schema / properties / niche / enum
      Previous value: -[
-  "auto_aftermarket",
-  "supplements",
-  "skincare",
-  "pet",
-  "home_kitchen"
-]New value: +[
+  "auto_aftermarket",
+  "supplements",
+  "skincare",
+  "pet",
+  "home_kitchen",
+  "apparel",
+  "jewelry_accessories",
+  "makeup",
+  "hair_care"
+]
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Despite annotations already marking the tool as non-destructive and idempotent, the description adds important behavior: free-plan masking with refs and monthly reveals, paid-plan export-row accounting, and account niche assignment. This also explains why readOnlyHint is false for a search operation, without contradicting the annotations.

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?

The description is a dense but front-loaded paragraph where each clause conveys scope, defaults, access rules, or cost behavior. There is no filler wording.

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 complex eight-parameter search with no output schema, it covers the critical access, masking, reveal, and quota behavior. Minor details such as result ordering or pagination behavior are not described, but limit and offset are handled by 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 the schema already documents parameter meanings and enum values. The description adds plan-level context, such as only the niche filter applying on the free plan, but it does not add parameter syntax or value semantics beyond what the schema provides.

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: searching US ecommerce brands flagged on the latest day for Meta ad changes, with explicit signal types and output fields. It distinguishes the result from sibling tools by routing masked rows to reveal_brand.

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?

Provides clear usage context: defaults to newly advertising and scaling brands, explains plan coverage, free-plan masking, and the reveal_brand path for masked rows. It does not explicitly compare this search against lookup_brand or check_store, so the alternative-selection guidance is incomplete.

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

All AdvertiserLeads toolsInspect
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.

Resources