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

Annotations already declare write, destructive, and open-world behavior, so the safety profile is carried. The description adds real behavioral context beyond that: optional setting groups (encoding, volumes, playback, transitions, video_fit, recording) and tags default sensibly, and a supplied schedule can itself start or stop broadcasting — a non-obvious side effect. It doesn't say what a failed platform/key combination returns, hence a 4 not a 5.

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?

Front-loaded with the required fields, then platform-specific key rules, then optional groups, then lifecycle ownership. Dense but every sentence carries information; the trailing 'Mirrors POST /api/v1/streams' is arguably filler for an agent but harmless.

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 14-parameter creation tool with nested objects and no output schema, the description covers what must be supplied, how optional groups behave, and how the object interacts with the start/stop lifecycle. The omission of any guidance on failure/auth requirements or the returned object is minor given annotations cover the write/destructive profile.

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%, so the schema already documents all 14 parameters, including nested objects and the key-format constraints. The description restates the required fields and key prefix rules, which is useful reinforcement but not meaningfully additive. Baseline 3 applies when the schema does the heavy lifting.

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?

The opening sentence gives a specific verb+resource ('Create a stream'), and the follow-up about status being managed by start_stream/stop_stream cleanly separates this creation tool from the lifecycle siblings. An agent can distinguish it from update_stream and start_stream without opening any 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?

It states a clear when-not: status/broadcasting is controlled via start_stream/stop_stream and scheduling, so the agent knows not to try to go live through this tool. The key-requirement rules per platform (none vs custom/instagram/rumble vs customsrt) are also usage-relevant. It stops short of naming update_stream as the mutation path for existing streams, so it isn't a full 5.

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