List in-progress config flows

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds value by naming the underlying WebSocket command, the error surface (`RuntimeError` on auth/WS failure), and returns a dict structure. It doesn't detail auth requirements or rate limits, but the WS-level failure disclosure is meaningful behavioral context beyond annotations.

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?

Front-loaded with the core purpose, then structured into named sections (Calls/Use when/Not for/Returns/Errors) that are easy to scan. Every sentence earns its place with no 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?

Output schema exists so return dict contents needn't be fully re-explained; the description skims the return fields, and it covers what an agent must know to call correctly: the WS command invoked, the lifecycle state being queried, the sibling relationship, and the error behavior. Complete for a complex integration-lifecycle tool.

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?

Zero parameters, so the baseline is 4 per the rubric. The description doesn't need to compensate for param coverage and correctly omits param discussion.

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?

States a specific verb and resource ('List config flows that were started but not yet finished') and explicitly distinguishes from siblings: 'Not for: flows already completed into a config entry — use system_list_integrations.' This lets an agent tell it apart from integrations_start_config_flow, integrations_get_config_flow, and system_list_integrations without opening a schema.

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?

Provides explicit when-to-use ('finding a flow_id left over from an earlier integrations_start_config_flow call, e.g. one waiting on discovery') and an explicit exclusion routing to an alternative sibling. This is the strongest possible usage guidance.

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