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

Annotations only declare a non-read-only, non-destructive, non-idempotent local mutation; the description goes well beyond that with return fields (video_url expiring after 7 days, duration_seconds, share_url), an AI-labelling disclosure, concurrency and daily quotas, the same-input replay behavior, and a full error taxonomy with recovery actions. The only nuance is that the identical-input replay described is somewhat idempotent-like while idempotentHint=false, but the dominant new-video-with-quota behavior is non-idempotent, so this is not a contradiction.

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?

Everything stated earns its place given the number of failure modes and limits, and the purpose plus return values are front-loaded. It is a single dense paragraph mixing returns, limits, example, and errors, so light structural separation would help, but there is no filler.

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 two-parameter generation tool the description covers the purpose, the quota and concurrency constraints, the caching behavior, and every recoverable error with a next action, and an output schema exists so return-value detail need not be restated. Nothing needed to call it correctly is missing.

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% and the enum/min/maxLength are already in the schema, so the baseline is 3. The description adds real meaning beyond it: the ~19-second speech ceiling (~15 s typical), the word-for-word fidelity requirement, the excluded personal-information content, and a concrete example call.

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 states a specific verb and resource ('Make a short video of one bitHuman house character saying `text` word for word, in its own voice') and distinguishes itself from siblings by routing conversational use to a per-reply pattern rather than talk_to_character and pointing at list_characters for character ids. An agent can tell what this produces without opening the 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 gives explicit when-to-use guidance ('To hold a conversation in character, write each reply yourself and call this tool once per reply') and names the alternative for the failure case (unknown character -> call list_characters). Limits, retry timing, and the replay-on-identical-input condition are all stated, so usage conditions are unambiguous.

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