Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Research ads

research_ads

Run open-ended ad research across platforms when sources aren't known upfront: compare angles, find what's working, and synthesize findings in an agentic loop.

Instructions

Open-ended ad research that needs JUDGMENT across platforms — comparisons, "what angle is working", "who else is doing this", anything where the right sources are not known up front. It is an agentic loop (several rounds of library pulls plus a written synthesis) and typically takes 30-60 seconds, so it is the WRONG tool for a question that names its own answer. For one named brand’s live ads use pull_competitor_ads; for one keyword or one advertiser on Meta use search_meta_ads — both are a single call and return in a few seconds. Spends credits — an agentic loop, so a handful rather than the one-call cost of a targeted search.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
brandNobrand name or profile object to tailor the research to; omit to use the workspace’s saved brand
queryYeswhat to research, e.g. "the longest-running protein-pancake ads on Meta"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "actions": {
-      "description": "follow-up actions the research loop suggested"
-    },
-    "reply": {
-      "description": "the research summary",
-      "type": "string"
-    },
-    "results": {
-      "description": "the found ads/videos (normalized card objects with served URLs)",
-      "items": {},
-      "type": "array"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Addedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, but do not explain why. The description supplies the missing behavior: it is an agentic loop of several library pulls plus a written synthesis, runs 30-60 seconds, and spends credits (a handful rather than a single-call cost) — which is exactly what justifies the non-read-only, non-idempotent profile. Return shape ('written synthesis') is also disclosed.

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 use case, then tradeoffs and routing, with zero filler sentences. It is dense and slightly long with nested quoted examples, but each sentence contributes either a routing rule or a behavioral fact.

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 an open-world agentic research tool with no output schema, the description covers cost, runtime, loop structure, and what comes back, plus sibling routing. Only minor gaps remain, such as how results are scoped or paginated, which are not essential to calling it correctly.

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 both parameters are already documented in the schema, and the description adds no format, syntax, or defaulting detail for query or brand. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ('open-ended ad research') and immediately scopes it with the judgment-based case it serves ('what angle is working', 'who else is doing this'). It positively distinguishes itself from the two nearest siblings, pull_competitor_ads and search_meta_ads, so an agent can route 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use ('needs JUDGMENT across platforms', right sources unknown up front) and when-not ('the WRONG tool for a question that names its own answer'), then names the two alternative tools with the exact condition that selects each. The latency and cost tradeoff is stated as the selection axis, leaving nothing to inference.

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