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

Annotations declare non-read-only, non-idempotent, open-world, non-destructive; the description adds valuable behavior beyond that — it reuses the original trigger payload and auto-discovers the trigger name. It still omits whether a new run ID is created, what failure returns, or any permission requirements.

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?

Two tight sentences, front-loaded with the action and scope, followed by the mechanism and the parameter-elimination note. 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?

For a three-parameter mutation tool with no output schema, the description covers purpose, precondition, and payload handling adequately. It leaves minor gaps around post-resubmit behavior and error cases, but nothing an agent must know to invoke it is missing.

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% (including the 'latest' shorthand for runName), so the baseline is 3. The description's note that no trigger-name parameter is needed adds context but is behavioral rather than clarifying an existing parameter's meaning.

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 ('Resubmit a failed or cancelled Power Automate flow run') plus the key scope constraint (only failed or cancelled runs) and the mechanism (live PA API, re-using the original trigger payload). This cleanly separates it from siblings like trigger_live_flow (creates a new run) and cancel_live_flow_run.

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?

Gives clear usage context: use it on a failed or cancelled run, and the original payload is reused rather than supplied. It does not explicitly name alternatives (e.g., trigger_live_flow for a fresh run) or state what happens if the run isn't in a resubmittable state.

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