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

No annotations are provided, so the description carries the full burden and largely succeeds: it discloses per-provider credit costs, the pause-tag syntax, that it is async (generation.id + polling), and host rendering behavior. It omits failure modes, rate limits, and whether credits are refunded on failure, keeping it just below the top band.

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?

Roughly five dense sentences, each front-loaded with a distinct payload: purpose, voice-selection workflow, cost matrix, pause-tag syntax, and return/polling contract. No filler or repeated schema content.

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?

With no output schema, the description proactively supplies the return contract ('generation.id — poll with wait_for_voiceover'), and it also covers cost and text-formatting concerns an agent would otherwise miss. Only the idempotencyKey parameter is left unexplained, a minor 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 description coverage is 86%, so the schema already documents nearly every parameter and a baseline of 3 applies. The description adds genuinely new meaning beyond the schema, notably the pause-tag syntax that governs the 'text' field and the voice-selection provenance (Eleven v3 list vs cloned vs MiniMax presets).

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 ('Generate a voiceover ... from a script') plus the target artifact class (social video, Reel or ad). An agent can distinguish this from create_music or create_voice_clone without opening any 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 an explicit prerequisite workflow ('Use list_voiceover_voices first and let the user pick') and a downstream step ('poll with wait_for_voiceover'), which is strong context. It never states when NOT to use it or contrasts directly with a conflicting sibling like change_voice, so it falls short of the full 5.

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