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

Annotations only give readOnlyHint=false; the description adds substantial context beyond that: it notifies the client as a side effect, returns a join URL and token scoped to the coach's side, and previews until confirm:true. Missing details like permission requirements or whether minutes are consumed, but this is well above the annotation baseline.

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?

A single compact sentence plus a short parenthetical; the action and result are front-loaded and nothing is wasted.

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, but the description covers the important return values (join URL and token) and the notification side effect, which is what an agent needs to call it safely. Lacks only minor operational details such as permissions or error 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?

Schema coverage is 100%: both clientId and confirm are documented in the schema with their semantics. The description's note about confirm-gating duplicates rather than extends the schema, 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 and resource ('Start an instant video call with a client') and adds the key differentiator from sibling join_*_video_call tools: this is an instant/ad-hoc launch, not joining an existing session. It also tells the agent what comes back (join URL and token).

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?

The confirm-gate parenthetical clearly explains the preview-then-execute workflow, which is strong usage guidance for a mutating tool. It does not explicitly name alternatives (e.g. join_session_video_call vs get_video_call_access) or state when not to use it, so it falls short of a 5.

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