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

Annotations indicate non-read-only, non-idempotent, non-destructive, but description adds some transparency by hinting at the follow-up action (`creations_show`) and the ability to pass either URLs or creation IDs. It lacks details on side effects, cost, or timing, which would be valuable beyond the annotations.

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?

The description is succinct and well-structured, using arrows and backticks to clearly separate concepts. It packs essential information in three short sentences without redundancy, making it easy to parse.

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?

Given the tool's complexity, it covers the core usage: modes, input sources, and the required follow-up. It omits potential details like output format, error handling, or parameter constraints, but with no output schema defined, these are less critical. The description is sufficient for a competent agent to use the tool correctly.

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 has zero parameter descriptions, so the description must compensate. It explains the `mode` parameter ('Omit for auto') and clarifies that inputs can be URLs or creation identifiers from related tools. However, it does not map these identifiers to specific parameters (audioUrl, imageUrl, videoUrl) and leaves other parameters (prompt, voiceId, resolution, folderReference) unexplained, covering only a small subset.

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?

Clearly states the tool's function: 'Make a character speak.' It distinguishes the two primary modes (image+audio → talking head, video+audio → lip sync) and mentions auto mode via `mode` omission, which uniquely identifies this tool among siblings.

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?

Provides explicit instructions: 'Omit `mode` for auto' and 'Pass asset URLs or a creation identifier (from...)'. It also directs to call `creations_show` afterward, indicating a workflow. However, it does not explicitly state when to prefer this tool over alternatives, though the description implies its unique purpose.

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