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

Annotations mark it non-readonly, destructive, open-world, non-idempotent. The description adds material context the annotations don't: ASYNC with projectId + polling, credit cost (min 25, ×2 at 1080p, +5 for voice change), and reuse semantics for the driving key. This exceeds the annotation bar substantially.

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?

Dense but every sentence earns its place: cost, async flow, prerequisites, batching tip, replay tip. Front-loaded with the core operation, 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 12-param async credit-spending tool with no output schema, the description covers cost, async behavior, prereqs, and reuse. It doesn't cover the half of params undocumented in the schema (name, prompt, sceneMatch), so an agent relying on the description alone would need the schema for those.

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 50%, so about half the params are undocumented in the schema. The description names the key inputs (characterR2Key, drivingVideoR2Key, r2Key from swap_upload) but doesn't explain name, prompt, sceneMatch, resolution, or the required file-name/duration pairs. Partial compensation, but gaps remain.

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 (swap) + resource (character image onto driving video) with a differentiating scope detail (optional range restoration). The reference to swap_import_character and swap_upload makes clear it's the downstream compositing step, distinguishing it from sibling import/upload tools.

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?

Explicit prerequisites (character r2Key via swap_import_character or swap_upload, driving-video r2Key from swap_upload), polling flow (poll get_job), and a concrete batching strategy (upload once, call repeatedly with different characters). The replay pathway via get_video is named. This is unusually complete routing guidance.

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