Create call

Runs one of the caller's activated tools and answers with its output.

POST /v1/tool/call

Addresshttps://api.hanzo.ai/v1/tool/call
MethodPOST
Operationpost_tool_call
AuthAuthorization: Bearer $HANZO_API_KEY

Runs one of the caller's activated tools and answers with its output.

This is the endpoint onto the tool plane's DYNAMIC half — the half no build-time catalogue can hold, because it is per-tenant: an org's connected connector actions, its authored skills, its agents and functions, and the tools of every external MCP server it registered. A tool's existence, its price and its activation are all rows, not code, so they cannot be known until the caller is.

One policy, the registry's: resolve by precedence, refuse an unactivated tool 403, settle a priced one through the x402 client or fail closed 402, then dispatch to the winning source bound to the caller's own (org, project). One metered unit, one audit record. A caller can only ever dispatch its own tools.

Discovery is GET /v1/tool — ?activated=true for the callable set.

Request

3 fields, body application/json (required).

FieldInTypeRequiredDescription
argumentsbodyobject—Arguments is the tool's own input object, passed through verbatim to whichever source owns it.
arguments.*bodyany—
namebodystring—Name is the tool to run, exactly as GET /v1/tool reports it.

Response

StatusBodyMeaning
200tool.toolResultok
defaultproblem-detailsrefused

200 body — 2 fields.

FieldInTypeAlwaysDescription
namebodystring—Name is the tool that ran.
resultbodyany—Result is the tool's own output, verbatim — its shape is the tool's, not this plane's.

Failure carries the platform error shape — see Errors.

Examples

hanzo tool call
import { Configuration, ToolApi } from 'hanzoai';

const api = new ToolApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postToolCall({ arguments: {}, name: "<name>" });
from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import ToolApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = ToolApi(client).post_tool_call(arguments={}, name="<name>")
cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.ToolAPI.PostToolCall(context.Background()).Execute()
if err != nil {
	return err
}
use hanzo_client::apis::{configuration::Configuration, tool_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = tool_api::post_tool_call(&cfg, Default::default()).await?;
import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.ToolApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new ToolApi(client).postToolCall();
curl -X POST https://api.hanzo.ai/v1/tool/call \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "arguments": {},
       "name": "<name>"
     }'

MCP reaches tool through the tool tool, which names its 17 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "list_tools"
         }
       }
     }'

Tool API · All Hanzo APIs · Interactive reference

Was this page useful?