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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the mutating/outbound nature is covered. The description adds value beyond that by disclosing the plan/trial authorization gate and the specific 403 rejection behavior, though it does not say whether an already-live stream errors or is idempotent.

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 short sentences, fully front-loaded with the action first, then the constraint and endpoint reference. No filler or redundancy.

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 single-parameter action with no output schema, the description covers the action, the authorization constraint, and the underlying endpoint, with annotations carrying the safety profile. Slightly incomplete on success semantics and idempotency behavior.

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?

Only one parameter ('stream') and the schema already documents it at 100% coverage as 'Stream UUID.' The description adds no format, sourcing, or lookup guidance for that identifier, so 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 ('Start') and resource ('broadcasting a stream to its platform'), making it immediately distinguishable from siblings like stop_stream, create_stream, or update_stream. The REST endpoint mirror (POST /api/v1/streams/{stream}/start) further pins down the exact operation.

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 a concrete precondition and failure mode: rejection with 403 when the plan/trial does not permit streaming. This tells the agent when the call will fail, but it does not explicitly contrast with stop_stream or state when a stream must already exist/is in a stoppable state.

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