Create a testimonial (AI model / persona)

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

Annotations only say this is a non-read-only, open-world, non-idempotent, non-destructive call. The description adds what an agent actually needs: 50-credit cost, 1–3 minute runtime, default blocking wait, the returned name (personId) and composite asset, consent recorded with timestamp and IP, and a content policy that refuses nudity or sexual photos.

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?

Front-loaded with the purpose and the downstream use, and every sentence carries information. It is a dense single paragraph with heavy semicolon chaining and a trailing ellipsis list of attributes, which slightly hurts scannability.

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 an 8-parameter, nested-object, credit-charging tool with no output schema, the description covers cost, latency, blocking behavior, return values, and the legal/ethical gate. The remaining gaps (locale, timeoutSec, projectId) are low-stakes plumbing, not decision-critical.

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?

At 50% schema coverage the description does real work: it explains the three photo views (left profile, front, right profile) as an identity composite, notes gender and age are required for `attributes`, lists the optional look fields, and gives accepted value formats in English (gender "Female", age "25-35"). However, `wait`, `timeoutSec`, `locale`, and `projectId` are never explained in the description, leaving a genuine gap.

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 ('Create a reusable TESTIMONIAL on the account') and defines what the entity is — a consistent, identity-locked person castable by name in vivid_generate_image. It also names the consuming sibling tool, so an agent can place it in the pipeline without opening anything else.

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 two explicit creation paths (`photos` for a real person, `attributes` for a from-scratch persona) with the conditions selecting each, and states a hard gating rule for `consent`: set true ONLY after the user confirms the pictured person is them or has consented, 'Never assume it.' The only thing absent is an explicit when-not-to-use-this-tool-elsewhere clause.

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