FlowiseAI/Flowise · error · Error

Received tool input did not match expected schema: ${JSON.st

Error message

Received tool input did not match expected schema: ${JSON.stringify(arg)}

What it means

Thrown inside ChatflowTool StructuredTool._call when parseWithTypeConversion(this.schema, arg) rejects. Identical to error 347 for the agentflow variant: arg is the LLM-supplied tool call input, this.schema is a zod schema, and the raw arg is JSON-stringified into the message so the caller can see what the model sent.

Source

Thrown at packages/components/nodes/tools/ChatflowTool/ChatflowTool.ts:292

        this.overrideConfig = overrideConfig
        this.returnDirect = returnDirect
    }

    async call(
        arg: z.infer<typeof this.schema>,
        configArg?: RunnableConfig | Callbacks,
        tags?: string[],
        flowConfig?: { sessionId?: string; chatId?: string; input?: string }
    ): Promise<string> {
        const config = parseCallbackConfigArg(configArg)
        if (config.runName === undefined) {
            config.runName = this.name
        }
        let parsed
        try {
            parsed = await parseWithTypeConversion(this.schema, arg)
        } catch (e) {
            throw new Error(`Received tool input did not match expected schema: ${JSON.stringify(arg)}`)
        }
        const callbackManager_ = await CallbackManager.configure(
            config.callbacks,
            this.callbacks,
            config.tags || tags,
            this.tags,
            config.metadata,
            this.metadata,
            { verbose: this.verbose }
        )
        const runManager = await callbackManager_?.handleToolStart(
            this.toJSON(),
            typeof parsed === 'string' ? parsed : JSON.stringify(parsed),
            undefined,
            undefined,
            undefined,
            undefined,
            config.runName

View on GitHub (pinned to abe4a8601a)

Solutions

1. Inspect the JSON-stringified arg to see what the model sent.
2. Improve tool description and add few-shot examples.
3. Loosen the schema where sensible; upgrade to a stronger tool-calling model if errors persist.

Example fix

// before
try {
  parsed = await parseWithTypeConversion(this.schema, arg)
} catch (e) {
  throw new Error(`Received tool input did not match expected schema: ${JSON.stringify(arg)}`)
}
// after
try {
  parsed = await parseWithTypeConversion(this.schema, arg)
} catch (e) {
  const reason = e instanceof Error ? e.message : String(e)
  throw new Error(`Received tool input did not match expected schema: ${JSON.stringify(arg)} (reason: ${reason})`)
}

function preflightSchema(schema: z.ZodTypeAny, arg: unknown) {
  const r = schema.safeParse(arg)
  if (!r.success) throw new Error(`Preflight schema violation: ${r.error.message}`)
}

function looksLikeToolArg(v: unknown): v is Record<string, unknown> {
  return typeof v === 'object' && v !== null && !Array.isArray(v)
}

try {
  return await chatflowTool.invoke(arg)
} catch (e) {
  const msg = (e as Error).message
  if (msg.startsWith('Received tool input did not match')) {
    // feed JSON.stringify(arg) back to the model with a corrective prompt
  } else throw e
}

When it happens

Trigger: LLM emitted JSON-as-string, omitted required fields, sent wrong types, or produced malformed JSON that parseWithTypeConversion cannot coerce.

Common situations: Weaker model with poor tool-calling; schema changed without prompt updates; truncated JSON from a model timeout.

Related errors

• Received tool input did not match expected schema: ${JSON.st
• Received tool input did not match expected schema
• Error parsing Zod Schema: ${exception}
• Received tool input did not match expected schema ${e}
• Unsupported type: ${typeInfo.base}

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/11b71b2add1e6ab0. Report an issue: GitHub.