Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Set the competitor watch

set_competitor_watch
DestructiveIdempotent

Set or stop a weekly watch on competitor ad libraries, reporting new ads by brand. Replaces the whole list; pass every brand each time, or an empty list to stop.

Instructions

Set (or STOP) this workspace's standing COMPETITOR WATCH — the weekly job that re-checks each named brand's ad libraries and reports what is NEW since last time. The same watch the web app's Ad Spy > Watching tab manages, and the same one the weekly digest email is sent from (turn that email on/off with update_settings({watchEmail})). This REPLACES the whole watched list, it does not add to it — pass every brand you want watched, every time. Max 5 brands (the server trims past that). Pass an EMPTY list to stop the watch entirely, which also clears the findings. Give a domain wherever you know one: Google Ads Transparency is looked up BY DOMAIN and is skipped for a brand without one, and the domain is what resolves the right Meta page for a brand with an ambiguous name. The run itself spends credits against the ad libraries (roughly 3 per brand on Meta, 1 each on Google and LinkedIn) and is hard-capped per run server-side, so an oversized watch is trimmed rather than allowed to run away. Setting the list is free; only a run spends. runNow:true runs it once IMMEDIATELY (a background job — it spends now) and then keeps the weekly cadence; leave it off and the first check is a week out. The country and the platform mix are NOT settable here — a re-set inherits whatever the pending run already carried (US / Meta for a watch that has never been configured otherwise). Read the findings back with list_watch_findings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
runNowNotrue to run one check immediately (spends credits now) instead of waiting a week for the first one
competitorsYesthe brands to watch — the COMPLETE list, replacing whatever was set before. Empty array = stop watching.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.161

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already mark it destructive and idempotent, but the description adds substantial context beyond that: max 5 brands, server-side trimming, credit costs (~3 per brand on Meta, 1 on Google/LinkedIn), hard-capped runs, immediate run via runNow, and that a re-set inherits prior country/platform. This is rich behavioral disclosure.

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-loads the core purpose and the critical REPLACE-vs-ADD distinction. Some sentences are dense with parenthetical asides, but every sentence carries operational value (costs, limits, alternatives). Slightly long but justified by complexity.

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 no output schema, nested objects, and multiple behavioral facets (destructive replace, credit spend, max limits, immediate run option, inherited settings), the description is remarkably complete. An agent would need no further investigation to call this correctly.

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 schema itself documents parameters. The description adds meaning beyond the schema: the REPLACE semantics of the competitors list, the empty-list stops behavior, the domain disambiguation value, and the runNow immediate-run behavior. This goes beyond the schema's mechanical descriptions.

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/STOP) and resource (the competitor watch) with the exact mechanism: a weekly job that re-checks named brands' ad libraries. Clearly distinguishes itself from siblings like list_watch_findings and pull_competitor_ads by naming them or describing its distinct role.

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?

Explicitly states when/why to use it, when not to (via alternative tools), and the critical semantic that it REPLACES the entire list rather than appends. Names update_settings({watchEmail}) for email control and list_watch_findings for reading results.

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