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

The description substantially exceeds the minimal annotations (readOnlyHint=false, etc.) by disclosing side effects (runs a flow), return fields (httpStatus, response body, triggerKind, runName), and the refusal of body for scheduled flows. It also clarifies that runName may be absent and directs to get_live_flow_runs otherwise—information annotations cannot convey.

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 longer than typical but every sentence earns its place: purpose first, then trigger-type details, then parameter guidance, then return notes, then exclusions. It is front-loaded and structured logically, though slightly dense for a quick scan.

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 tool that triggers flows with no output schema, the description covers all essential runtime concerns: what inputs to pass, how to handle flows that take no inputs, what the response contains, and which trigger types are unsupported. It also points to the sibling tool for run details, making it self-contained for correct invocation.

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?

While schema coverage is 100% and each parameter is already documented, the description adds critical usage semantics for the body parameter: 'Pass trigger inputs as `body`' and 'Omit for flows that expect an empty body,' plus the refusal rule for recurrence flows. This goes beyond the schema's generic 'JSON body to POST' and helps the agent construct correct calls.

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-resource pair ('Run a flow on demand') and immediately distinguishes itself from siblings by naming the alternative tool for retrieving runs ('use get_live_flow_runs otherwise'). The trigger-type coverage (Request, recurrence) is explicit, so an agent can tell it apart from get_live_flow_trigger_url or get_live_flow without opening schemas.

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 conditions: works with Request triggers (HTTP, Button, PowerApps) and recurrence flows, and clearly states when NOT to use it (Automated connector triggers) and what to do instead (they only fire from their source event). Also notes the refusal of body for scheduled flows, adding a behavioral caveat that prevents misuse.

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