Messages API tool use

POST /v1/messages accepts Anthropic’s standard tool definitions. tool_use and tool_result content blocks pass through to the upstream provider with no Kindo-specific wrapping.

Define a function tool

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 512,
  "tools": [
    {
      "name": "get_weather",
      "description": "Get the current weather for a city.",
      "input_schema": {
        "type": "object",
        "properties": {
          "location": { "type": "string" }
        },
        "required": ["location"]
      }
    }
  ],
  "messages": [
    { "role": "user", "content": "What is the weather in San Francisco?" }
  ]
}

Anthropic tool definitions use name / description / input_schema (different from Chat Completions’ nested function object).

Round trip

Step 1 — initial request

Submit the request above.

Step 2 — assistant message with `tool_use`

{
  "id": "msg_01",
  "role": "assistant",
  "content": [
    {
      "type": "tool_use",
      "id": "toolu_01",
      "name": "get_weather",
      "input": { "location": "San Francisco, CA" }
    }
  ],
  "stop_reason": "tool_use"
}

stop_reason: "tool_use" is the canonical signal that the model wants you to run a tool.

Step 3 — execute the tool client-side

Run get_weather({ location: "San Francisco, CA" }) in your application.

Step 4 — submit the result

Return the result as a tool_result content block in a user message. Re-include the prior assistant message and re-include tools so the model has the schema:

curl -X POST https://api.kindo.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $KINDO_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 512,
    "tools": [
      {
        "name": "get_weather",
        "description": "Get the current weather for a city.",
        "input_schema": {
          "type": "object",
          "properties": { "location": { "type": "string" } },
          "required": ["location"]
        }
      }
    ],
    "messages": [
      { "role": "user", "content": "What is the weather in San Francisco?" },
      {
        "role": "assistant",
        "content": [
          {
            "type": "tool_use",
            "id": "toolu_01",
            "name": "get_weather",
            "input": { "location": "San Francisco, CA" }
          }
        ]
      },
      {
        "role": "user",
        "content": [
          {
            "type": "tool_result",
            "tool_use_id": "toolu_01",
            "content": "{\"temperature\":68,\"unit\":\"fahrenheit\"}"
          }
        ]
      }
    ]
  }'

The tool_use_id on the tool_result block must match the id on the originating tool_use block.

Step 5 — final answer

{
  "id": "msg_02",
  "role": "assistant",
  "content": [{ "type": "text", "text": "It's 68 °F in San Francisco." }],
  "stop_reason": "end_turn"
}

`tool_choice`

Anthropic’s tool-choice format:

Value	Behavior
`{ "type": "auto" }` (default)	The model decides whether to call a tool.
`{ "type": "any" }`	The model must call at least one tool.
`{ "type": "tool", "name": "..." }`	The model must call exactly that tool.