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

Annotations already declare idempotentHint=false and destructiveHint=true, and the description goes well beyond them: duplicate-broadcast risk on retry, the already-running/already-scheduled short-circuit that returns the existing live id, and platform-level limits (max stream length, 8-hour Facebook-only cap, unsupported thumbnails/announcements).

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 critical constraint (non-idempotent, do not retry on timeout) is front-loaded in the second paragraph, and the limits are separated into scannable bullets. Slightly verbose in framing ('Honest limits, so you do not promise the customer...') but no sentence is redundant.

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?

No output schema exists, and the description only implicitly signals the return value ('returns the existing live id'), so an agent lacks the full success-response shape. Everything else an agent needs to invoke it safely is present, including the retry and status-check protocol.

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% and there is a single required parameter, so the schema already documents projectId and its source tool. The description adds no format or constraint detail beyond that, so the baseline 3 applies.

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 ('Start streaming a project to its destinations immediately') and explicitly enumerates the project shapes it applies to. An agent can distinguish it from livereacting_schedule_stream and livereacting_stop_stream 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?

Explicitly covers when to use it, when NOT to retry after a timeout, the exact alternative to consult (livereacting_get_stream_status), and how to interpret that status (PREPARING/LIVE vs OFFLINE) before re-calling. This is a complete routing and retry policy.

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