Start a Homey flow

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

The description goes beyond the annotations in crucial ways. The annotations state destructiveHint=true and readOnlyHint=false, but the description explains the real-world consequences: 'a flow can unlock a door, open a window covering, turn on the heating or send a message.' It also clarifies that it is 'a real execution and not a preview,' which is a critical behavioral trait not captured by the annotations. This fully informs the agent of the potential impact.

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 two sentences, front-loaded with the main action ('Runs an existing flow immediately'), followed by essential warnings and scope. Every sentence earns its place: the execution nature, the consequence examples, the precaution, and the coverage of standard and advanced flows. No fluff.

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 tool is straightforward with a single parameter and no output schema, so the description is largely complete. It covers what the tool does, its side effects, and a safety precaution. However, it doesn't explicitly state the return value (though without an output schema, it may be minimal), and it doesn't mention error conditions (e.g., flow not found), but these are minor gaps given the simplicity. No annotations like openWorldHint would suggest further context, so a 4 is justified.

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?

The schema already has 100% coverage for the single parameter 'flow', describing it as 'Flow id or flow name.' The description does not add additional syntax or format details beyond what the schema provides, but it does imply that the flow must exist and be a valid flow. Since the schema is fully descriptive, the baseline of 3 is appropriate.

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 clearly states the tool's purpose: 'Runs an existing flow immediately.' It uses a specific verb ('Runs') and resource ('existing flow'), and distinguishes itself from sibling tools like homey_flow_validate (which presumably only checks validity) and homey_flow_create (which creates new flows). The phrase 'exactly as if its trigger had fired' provides precise semantics.

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 explicit guidance on when to use this tool: when you want to execute a flow immediately. It also warns against using it without knowing the flow's actions: 'Read the flow with the flow tools before starting it if you are not certain what it does.' This is direct advice on a precautionary alternative, effectively telling the agent when not to use it (i.e., without prior inspection).

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