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

Annotations already flag destructiveHint, idempotentHint and openWorldHint, and the description adds the operationally critical facts they cannot express: credits are charged only on success, the result is an id to poll with get_generation, and OAuth or an 'Authorization: Bearer acd_live_…' header is required. It also spells out the legal/consent condition attached to image_rights_consent, which is exactly the kind of beyond-schema behavior an agent must know before calling.

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 core purpose and the input alternatives come first, followed by prerequisites, return/polling behavior and billing, then auth last — a sensible front-loading. The OAuth/API-key block is somewhat verbose relative to the rest, but it is genuinely actionable rather than 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 destructive, credit-consuming, open-world generation tool with 8 parameters, the description covers the source-of-truth for quote_id, the consent gate, billing semantics, and the follow-up step (poll get_generation). An output schema exists, so the lack of return-field detail is not a 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 coverage is already 100%, so the baseline is 3; the description nevertheless adds meaning the schema doesn't convey on its own, such as template being an alternative to image_url, quote_id's provenance (estimate_ad_cost kind "ugc"), and that consent must be given by the person rather than assumed. It stops short of contrasting voice/language/ambience choices, so not a 5.

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+resource ('Make a UGC-style creator video') and immediately disambiguates the two input modes: catalogue creator via list_ugc_avatars/template, or the person's own photo via image_url, both lip-synced to a script. This distinguishes it from siblings like generate_avatar and generate_video without the agent needing to open 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 the full prerequisite chain: a quote_id from estimate_ad_cost with kind "ugc", and image_rights_consent=true given by the person, plus which sibling supplies the template. It names the alternative inputs but does not explicitly say when to prefer generate_video/generate_avatar over this tool, so it falls just short of a perfect routing statement.

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