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

Annotations only declare the generic profile (not read-only, not idempotent, not destructive), so the description carries real weight and delivers it: it spends account credits, explains the talking-cost relationship to avatar models, states the consent/rights gate for motion and swap, and says it returns a job (async). It does not cover job lifecycle details such as awaiting, cancelling, or failure behavior, which matters for a job-returning mutation.

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?

Three dense sentences, front-loaded with purpose, then modes and cost, then prerequisites. Each sentence carries distinct information (mode semantics, credit cost, eligibility/consent), so nothing is filler, though the parenthetical '(a picture)' and the closing consent sentence are slightly compressed for the amount of constraint they encode.

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 correctly signals the async contract ('returns a job') and covers prerequisites, rights gating, and cost for a 16-parameter tool that is fully schema-documented. It leaves the agent to discover job retrieval via siblings (get_job, wait_job), which is a minor gap rather than a blocking one.

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 100%, so the baseline is 3, but the description adds genuine meaning by mapping behavior to mode: talking = speak a line, motion = follow a reference clip, swap = replace the person in a clip, product = hold a product picture. This lets an agent infer which of the 16 parameters apply to the chosen kind, beyond the schema's per-parameter prefixes.

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?

Opens with a specific verb and resource ('Puts a saved person on screen and returns a job') and immediately enumerates the four modes (talking, motion, swap, product), so an agent knows exactly what class of output this produces. The 'saved person' scope and the per-mode behaviors distinguish it from generic siblings like ugcfans_make_video even without naming them.

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 strong preconditions: the person must be saved with a portrait and, if real, recorded consent at ugc.fans/library, and motion/swap additionally require rights_confirmed: true set only after the person confirms use of the source clip. It also names ugcfans_list_models for pricing context. It stops short of routing the agent away from this tool toward specific alternatives, so it is clear context without explicit exclusions.

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