Return the next step for a flow. Pass the goal (flow id) and the id of the last completed step (omit after for the first step). Run each step's detect command FIRST and skip the run command when detection passes. The design step also returns that flow's complete starter ALTER_INTEGRATION.md.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | The flow id (setup goal or modify operation). | |
| after | No | Id of the last completed step (e.g. "2", "3a"). |
Changes observed during successful MCP inspections.
Input schema / properties / goal / enumPrevious value: -[
- "user-data",
- "backend-secret",
- "agent",
- "add-provider",
- "add-secret",
- "add-agent",
- "rotate-key",
- "manage-grant"
-]New value: +[
+ "user-data",
+ "backend-secret",
+ "agent",
+ "add-provider",
+ "add-secret",
+ "add-agent",
+ "rotate-key",
+ "manage-grant",
+ "set-policy"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states that the design step also returns a complete starter ALTER_INTEGRATION.md, and it instructs the agent to run detect before run, which implies the step includes commands. These details go beyond a generic 'returns the next step' and give the agent actionable knowledge about side effects and outputs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences with no redundancy. The core purpose is front-loaded, followed by precise usage instructions. Every sentence earns its place: the first states the purpose, the second explains parameter handling, and the third gives the detect/run rule and the extra design step behavior. No unnecessary words or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's purpose, parameter usage, and key behavioral notes (detect/run sequence and the design step's extra return). Since there is no output schema, the description could have described the step's structure more explicitly, but it gives enough context for an agent to call the tool and handle the result correctly. The lack of error-case or edge-case detail prevents a perfect score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the schema descriptions already cover the parameters (100% coverage), the description adds value by clarifying that 'goal' is a flow id and by instructing the agent to omit 'after' for the first step. This is not present in the schema and directly affects how parameters are used, so the description enriches the schema semantics rather than just repeating them.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear verb-object statement, 'Return the next step for a flow,' and immediately identifies the two required inputs (goal and after). It also clarifies the 'goal' parameter as a flow id, which is a meaningful addition. While it does not explicitly compare to siblings, the action is specific enough that no sibling appears to overlap with this purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides concrete usage instructions: how to pass parameters (including omitting 'after' for the first step) and how to consume the result ('Run each step's detect command FIRST and skip the run command when detection passes'). It does not name alternatives or say when not to use this tool, but the guidance is actionable and specific, so it earns a 4 rather than a 3.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.