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

Annotations already provide idempotentHint=true (with readOnlyHint=false and destructiveHint=false), but the description adds meaningful behavioral context beyond them: it discloses the pre-read mechanism ('Reads the current flow state first and only issues the start/stop call if a state change is actually needed') and documents the return payload even though no output schema exists. This is genuinely useful, non-redundant disclosure.

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?

Three tight sentences with zero filler. The core purpose is front-loaded in sentence one, scope in sentence two, and behavioral/return details in sentence three. Every sentence earns its place.

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?

For a 3-parameter mutation tool with no output schema, the description covers purpose, scope, idempotent behavior, and return values. The only notable gap is that it doesn't specify behavior in the no-op case (when the flow is already in the desired state), though the pre-read sentence strongly implies a safe skip.

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?

Schema description coverage is 100%, so the schema already documents all three parameters, including the Started/Stopped enum for state. The description's 'start or stop' phrasing mirrors the enum values rather than adding new meaning, so it doesn't compensate or extend beyond the schema. Baseline 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 opens with a specific verb phrase, 'Start or stop a Power Automate flow', identifying the exact action and resource. It further clarifies scope ('any environment you have access to') and is clearly distinguishable from siblings like trigger_live_flow (runs) and cancel_live_flow_run (run cancellation) without requiring schema inspection.

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 intended use is implied by the action phrase and the live-flow scope, but the description never names alternatives or exclusion conditions. Notably, it doesn't address the closely related set_store_flow_state sibling, so an agent must infer the live-vs-store distinction from tool naming alone rather than explicit guidance.

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