google-flow-mcp

Overview Schema Source Related Servers Discussions Admin

Chat with the Flow agent

flow_agent_chat

Send messages to Flow's creative agent to brainstorm, write prompts, and generate content; attach character mentions and approve credit spend only within set limits.

Instructions

Send a message to Flow's creative agent (brainstorms, writes prompts, generates). character_ids are attached as mentions. If it asks to spend credits it is approved only when the quoted cost <= max_credits (default 0 = never); otherwise it stays pending for flow_agent_respond.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "message": "<message>"
    },
    "name": "flow_agent_chat"
  }
}

Input Schema

Name	Required	Description
`message`	Yes
`project_id`	Yes	Flow project id (from flow_list_projects).
`max_credits`	No
`new_session`	No
`character_ids`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 27, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and discloses meaningful behavior: character_ids become mentions, credit spends are gated by max_credits with a default of 0 meaning 'never', and a denied spend leaves the request pending for flow_agent_respond. It omits return format and session semantics, but the approval gating logic is unusually well explained for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the core action before the mention and credit mechanics. Near-optimal, though the mid-sentence parenthetical and the credit clause are slightly compressed.

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?

For a side-effecting, unannotated, output-schema-less tool, the description covers purpose, the credit-approval branch, the pending handoff, and the mention behavior. The only real gap is the unexplained new_session parameter, which a caller could trip over.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 20% (project_id only), so the description must compensate, and it does for two of the three undocumented params: character_ids ('attached as mentions') and max_credits (approval threshold, default 0 = never). The new_session boolean remains unexplained in both schema and description.

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?

States a specific verb ('Send a message') and resource ('Flow's creative agent') and clarifies the agent's capabilities (brainstorms, writes prompts, generates). It is distinguishable from flow_agent_respond, which it names, but the differentiation is only partial since respond is a continuation rather than a competing entry point.

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

Usage Guidelines3/5

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

The description implies usage context and names flow_agent_respond as the follow-up for pending approvals, which is genuinely useful. However, it never states when to prefer this over flow_agent_respond to initiate work, nor when to flip new_session, so an agent must infer the entry-point conditions.

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