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

Annotations only give openWorldHint and destructiveHint=false, so the description's disclosure that the call may be rejected with 403 when the plan/trial disallows streaming is real added value for predicting failure. It stops short of covering idempotency, what happens if the stream is already live, or the response shape.

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 short sentences, action-first, no filler. Each sentence carries distinct information: what it does, the failure mode, and the API mapping.

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 one-parameter action tool with no output schema, purpose, failure mode, and endpoint mapping are all present. Only the state transition semantics (already-streaming behavior, return value) are left implicit.

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?

The schema documents the single 'stream' parameter at 100% coverage (Stream UUID), so the description need not restate it. It adds no format or identifiability detail beyond the schema, matching the baseline for fully-covered params.

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 with scope ('Start broadcasting a stream to its platform'), which cleanly separates it from create_stream, stop_stream, and get_stream. The endpoint mirror (POST /api/v1/streams/{stream}/start) reinforces exactly which operation this is.

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?

Usage is implied by the verb and the sibling set (start vs stop_stream), and the 403/plan nuance hints when calls fail, but there is no explicit statement of when to pick this over alternatives or any preconditions (e.g. must a stream be configured with destinations first).

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