Horizontal: tested MCP servers, agent cases, top apps

Startup markets that are forming, and their stage

search_trends

Read-onlyIdempotent

Find markets from Horizontal's Startup Trends: startup markets that are forming, each with its stage (emerging, heating up, overheated or cooling) set by a published rule from eight checks of builders, buyers, proof of money and signs of crowding, a verdict on whether it is worth entering now and how, and its headline figures. Every figure has a source and says who claims it. Analysis, not investment advice.

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_trends"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	No	What the market should be about, in English or Chinese: "ESP32", "AI glasses", "短剧", "vibe coding". Leave it out for every market.
`stage`	No	Only markets at this stage: emerging (More people are building or buying, but nobody has shown checkable money yet.); heating (More people are paying, small teams have made money someone checked, and fewer than three signs of crowding show.); overheated (Three or more of the five signs of crowding: hype ahead of sales, a price war, giants moving in, money cooling, high churn.); cooling (Fewer people are paying, and fewer are building or the money is leaving.)
`language`	No	The language of the words in the answer.	en

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already establish read-only, closed-world, idempotent behavior. The description adds substantive context beyond that: stages follow a published rule from eight checks, results include a verdict and sourced headline figures, and it carries an 'analysis, not investment advice' disclaimer. It still omits ordering and pagination, but the added disclosure is meaningful.

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?

The core purpose is front-loaded, but the first sentence is a dense run-on that packs methodology, output fields, and stage semantics into one clause chain. It remains readable and only three sentences long, but it could be split and trimmed.

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?

No output schema exists, so the description needs to explain what comes back; it does so by naming stage, verdict, headline figures, and source attribution. For a read-only search tool with schema-defined filters, that is largely complete, though result ordering and pagination are unaddressed.

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 coverage is 75% and the query, stage, and language parameters are well documented in the schema; only limit lacks a schema description. The description adds essentially no parameter guidance and even uses 'heating up' where the enum says 'heating', so it does not improve on the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb-resource: 'Find markets from Horizontal's Startup Trends,' and enumerates the returned stage, verdict, and headline figures. It is distinguishable from generic get_* tools by its search framing, but it never explicitly contrasts itself with the sibling get_trend.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

It never states when to use this search versus get_trend or the other search_* tools, nor any prerequisites or exclusions. The only usage signal is the implicit 'Find markets' framing, so guidance is essentially absent.

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

All Horizontal: tested MCP servers, agent cases, top apps tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?