Skip to main content
Glama
Hermoso

Hermoso

Official

Set the market radar

set_competitor_watch
DestructiveIdempotent

Configure a weekly or daily competitor watch to track rivals' new ads, 30-day winners, niche trends, top posts, and content ideas; set competitors and topics, or stop tracking by clearing both.

Instructions

Set, change or stop a brand's MARKET RADAR (the standing competitor watch; Ad Spy > Watching in the web app; each brand has its own), run weekly or daily: newAds (what watched brands launched), winners (their ad passing 30 days running), trends + topPosts (formats and most-viewed posts for niche topics), ideas (3 to make). Only what you pass changes. competitors / topics REPLACE their lists (max 8 brands, 5 topics); both empty stops it and clears findings. auto:true picks 3-5 competitors, 2-3 similar brands and 2-3 topics from the saved brand or seed (one model call, billed at its token cost). dryRun:true quotes one check, saves nothing. Saving is free; each check holds its quote first and is skipped when the balance is short. runNow is refused while a check runs or just after one finished. Read it with list_watch_findings.

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": "set_competitor_watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
autoNotrue picks competitors, similar brands and topics from the saved brand or seed; bills one model call at its token cost
seedNofor auto: a website, brand or niche
brandNoprofile id/name from list_brands, this call only
emailNothe weekly email
forceNowith runNow: check again right after a check, allowed once what is watched changed
dryRunNotrue quotes one check and saves nothing
runNowNocheck now (spends now)
topicsNoniche search phrases, e.g. "protein breakfast"
cadenceNoweekly (default) or daily check
modulesNoon/off; omitted keep theirs
competitorsNothe COMPLETE brand list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.484
    • changedInput schema / properties / auto / description
      Previous value: -"true picks competitors, similar brands and topics from the saved brand or seed; costs a few credits"New value: +"true picks competitors, similar brands and topics from the saved brand or seed; bills one model call at its token cost"
  2. Changed10 schema fields changedv0.1.465
    • addedInput schema / properties / auto / description
      Added value: +"true picks competitors, similar brands and topics from the saved brand or seed; costs a few credits"
    • addedInput schema / properties / cadence / description
      Added value: +"weekly (default) or daily check"
    • addedInput schema / properties / competitors / items / properties / kind / description
      Added value: +"competitor (head-to-head rival) or similar (adjacent brand)"
    • addedInput schema / properties / competitors / items / properties / name / description
      Added value: +"brand name to watch"
    • addedInput schema / properties / dryRun / description
      Added value: +"true quotes one check and saves nothing"
    • addedInput schema / properties / modules / properties / ideas / description
      Added value: +"true includes three ideas to make from the findings"
    • addedInput schema / properties / modules / properties / newAds / description
      Added value: +"true includes new ads the watched brands launched"
    • addedInput schema / properties / modules / properties / topPosts / description
      Added value: +"true includes the most-viewed posts for the topics"
    • addedInput schema / properties / modules / properties / trends / description
      Added value: +"true includes formats trending in the topics"
    • addedInput schema / properties / modules / properties / winners / description
      Added value: +"true includes watched ads that have run 30 days"
  3. Changed15 schema fields changedv0.1.454
    • addedInput schema / properties / auto
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / brand
      Added value: +{
      +  "description": "profile id/name from list_brands, this call only",
      +  "type": "string"
      +}
    • addedInput schema / properties / cadence
      Added value: +{
      +  "enum": [
      +    "weekly",
      +    "daily"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / competitors / description
      Previous value: -"the brands to watch — the COMPLETE list, replacing whatever was set before. Empty array = stop watching."New value: +"the COMPLETE brand list"
    • changedInput schema / properties / competitors / items / properties / domain / description
      Previous value: -"its domain, e.g. ridge.com — required for Google Ads Transparency, and what disambiguates a common brand name on Meta"New value: +"e.g. ridge.com: Google is read by domain, and it finds the right Meta page"
    • addedInput schema / properties / competitors / items / properties / kind
      Added value: +{
      +  "enum": [
      +    "competitor",
      +    "similar"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / competitors / items / properties / name / description
      Removed value: -"the brand name, as it advertises"
    • addedInput schema / properties / dryRun
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / email
      Added value: +{
      +  "description": "the weekly email",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / force
      Added value: +{
      +  "description": "with runNow: check again right after a check, allowed once what is watched changed",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / modules
      Added value: +{
      +  "description": "on/off; omitted keep theirs",
      +  "properties": {
      +    "ideas": {
      +      "type": "boolean"
      +    },
      +    "newAds": {
      +      "type": "boolean"
      +    },
      +    "topPosts": {
      +      "type": "boolean"
      +    },
      +    "trends": {
      +      "type": "boolean"
      +    },
      +    "winners": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
    • changedInput schema / properties / runNow / description
      Previous value: -"true to run one check immediately (spends credits now) instead of waiting a week for the first one"New value: +"check now (spends now)"
    • addedInput schema / properties / seed
      Added value: +{
      +  "description": "for auto: a website, brand or niche",
      +  "type": "string"
      +}
    • addedInput schema / properties / topics
      Added value: +{
      +  "description": "niche search phrases, e.g. \"protein breakfast\"",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "competitors"
      -]
  4. Addedv0.1.161

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: only passed fields change, competitors/topics are replacement lists with caps, both-empty destroys findings, auto burns a billed model call, dryRun only quotes, saving is free but checks reserve quote and skip on low balance, and runNow is refused during or right after a check. This matches and enriches the destructiveHint and idempotentHint semantics.

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?

Front-loaded with the core definition and then dense operational notes; almost every clause adds decision-relevant information. It is a bit semicolon-heavy and reads like a compressed paragraph, but there is little waste for an 11-parameter mutation tool.

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 destructive, credit-spending, 11-parameter mutation with no output schema, the description covers mutation scope, clearing behavior, cost mechanics, dry runs, refusal windows, and where to read results. An agent has what it needs to call it correctly without opening other documentation.

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, but the description adds replacement semantics for competitors/topics, max list sizes (8 brands, 5 topics), auto's selection counts, and the billing/quote behavior of dryRun and runNow. These are meaningful constraints not fully captured in the schema.

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 set (set/change/stop) and a precise resource (the brand's MARKET RADAR, mapped to Ad Spy > Watching, one per brand). It also distinguishes the tool from the sibling that reads it (list_watch_findings), so an agent can tell what it configures versus what it reads.

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 clear operational routing ('Read it with list_watch_findings'), the stop condition (both empty clears findings), and when runNow is refused. It does not compare against adjacent discovery tools like find_competitors, research_ads, or competitor_teardown, so the alternative-selection guidance is strong but not exhaustive.

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

Deploy Server

Other Tools