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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description goes beyond that by disclosing the interaction model — the result is a picker card, the user's choice arrives as their next message, and the agent must not restate the list — which is genuinely useful context. It says nothing about ordering, voice availability when no voices match the language, or how the 'more behind a button' expansion is triggered.

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 what the card is and what it is not, followed by behavioral rules, so the important routing information comes first. The middle clause about country flags and samples is somewhat verbose, though it does describe the returned card.

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?

The tool takes one optional parameter, has no output schema, and its annotations cover the safety profile, so the description is broadly adequate. What is missing is what happens when the language has no matching voices or how the agent should respond to the picker's follow-up message beyond calling it alone.

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 single parameter is already documented with its format, default, and meaning. The description only implies that language filters which voices appear ('voices that speak the language'), adding marginal meaning beyond 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?

States a concrete resource (the ClipFlux narrator picker card shown on its own) and a concrete effect (voices speaking the given language, with flags and samples). It explicitly distinguishes itself from list_looks, which handles choosing look and narrator together, so an agent can route correctly 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 both the when ('for changing only the narrator') and the named alternative with its selecting condition ('choosing a video's look and narrator together is list_looks'). It also adds two explicit invocation rules: call it on its own, and do not enumerate the voices in the reply.

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