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

Annotations only say non-readonly, non-destructive, open-world; the description goes well beyond by disclosing the automatic leak check, that the URL and embed code are returned, the embed_origins allow-list semantics, the one-agent-on-camera limit, the requirement to be in the room first, that the key is vaulted and never shown again, and the verified-owner prerequisite.

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 mode-by-mode structure is front-loaded and every clause carries information, but the semicolon-chained sentences run long and the opening is a fragment ("to \"page\" opens..."), which costs some readability.

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 6-parameter, three-mode dispatch tool with an output schema, the description covers selection, prerequisites, side effects, follow-up (stop_session), and key handling. Nothing an agent needs in order to call it correctly is missing, and return values are correctly left to the output schema.

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?

With 50% schema coverage, the description compensates well: it maps `to` values to the required companion parameters, explains what embed_origins unlocks, and clarifies that meetingburner_key is supplied once and retained. Only `audience` and `id` go unmentioned, and both are already documented in the schema.

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 description names a specific verb and resource and then breaks the tool's behavior into its three modes ("page", "meeting", "meetingburner_room"), stating what each does. An agent can distinguish the modes without opening the schema, and the personal-page vs in-call distinction is unmistakable.

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 supplies concrete conditions for each mode: page needs only the id (plus optional embed_origins), meeting requires meeting_url, and meetingburner_room requires a room link plus a one-time meetingburner_key, with the constraint that you must already be in the room. It also routes the reverse action to stop_session. It stops short of contrasting itself with siblings like start_session or test_nod, so it is not a full selection guide.

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