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

Annotations already declare this is a non-read-only, non-idempotent mutation, so the bar is lower, yet the description adds real value: the session is paid, it rejects over-limit or unprepared starting conditions, voice and text share one conversation, and the returned avatarSessionId is needed for follow-up calls. It stops short of describing permissions, what happens on timeout, or stop semantics.

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?

Four short sentences, front-loaded with the core action and consent requirement before prerequisites and the follow-up hint. Dense and mostly waste-free, though 'Voice and text use one conversation' is slightly cryptic without further framing.

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 paid, non-idempotent session-start with no output schema, the description supplies the cost/duration constraints, failure modes, and the key return value (avatarSessionId) needed to continue the session. It omits any mapping of the required workspaceId/characterId identifiers, which leaves a small gap.

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 0%, so the description is the only source of parameter meaning; it explains maxCostUsd and maxSessionSeconds as the cost ceiling and duration bound, but says nothing about workspaceId, characterId, endUserId, or conversationId. Partial compensation for a six-parameter tool.

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 a paid live video conversation') and implicitly positions itself among siblings by telling the agent to retain avatarSessionId for send_live_avatar_message and stop_live_avatar_session. An agent can distinguish this from quote_live_avatar_session, prepare_live_avatar, and get_live_avatar without opening a 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?

Gives a clear gating condition ('after an explicit user request') and reveals prerequisites by noting it rejects an unprepared avatar and an over-limit reservation, which implies prepare_live_avatar and a quote/cost check must precede it. It does not, however, name those sibling tools explicitly as required alternatives.

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