# Agent Search Query Builder

> Agent Search Query Builder is a paid API for AI agents from agent-product-normalizer.vercel.app, paid per call via x402, $0.0015/call, status unknown (last checked 2026-09-18).

Compresses a verbose user task description into concise, search-engine-ready query variants for downstream web or product searches

## Facts

- Endpoint: GET https://agent-product-normalizer.vercel.app/api/v1/make-search-query
- Price: $0.0015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-search-query-builder-0d024d49
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jNEUJUstuc1bGJtol4FXk

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-search-query-builder-0d024d49
```

Example prompt: Take this messy task description and compress it into clean, search-engine-ready query variants: 'I need to find a durable waterproof hiking backpack with at least 50L capacity that works well in cold climates, has good lumbar support, and costs under $200 — ideally from a brand that's well-reviewed by serious hikers.'

## When to prefer this

Choose this endpoint when an agent has received a long, unstructured user request and needs to issue web or product searches efficiently without wasting tokens on verbose queries. It is particularly well-suited for multi-step agent workflows where a retrieval step follows user input, and compactness and precision of the search terms directly impact downstream result quality. Prefer it over manual keyword extraction when the task is ambiguous or multi-faceted and multiple query variants are valuable.

## Known failure modes

- Missing required 'task' query parameter returns a validation error
- Extremely short or content-free task strings may produce low-quality or generic queries
- Tasks exceeding the 20,000 character limit will be rejected
- Non-English or highly domain-specific jargon may produce poorly generalized queries
- Network or service unavailability on the Vercel deployment returns 5xx errors

## How this service works

Compress a verbose user task into search-engine-ready query variants

## Output

The endpoint returns one or more compact, search-engine-optimized query strings derived from the input task. These variants are suitable for direct use in web search engines, product catalogs, or knowledge bases, reducing token overhead and improving retrieval precision for downstream agent steps.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "task"
     ],
     "properties": {
      "task": {
       "type": "string",
       "maxLength": 20000,
       "description": "Messy task to convert into a compact search query"
      }
     },
     "additionalProperties": true
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-search-query-builder-0d024d49/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-product-normalizer.vercel.app](https://www.zero.xyz/host/agent-product-normalizer.vercel.app/llms.txt)