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

Adds information annotations don't carry: it costs 1 credit, credits are refunded on failure, and it returns both a preview image and a vault asset id. This meaningfully supplements the destructive/non-idempotent/openWorld hints. It stops short of disclosing any rate limits, auth requirements, or generation latency.

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?

Four sentences, each carrying distinct payload: purpose/ordering, cost/refund, return shape, and the reference-photo workflow. The key scoping constraint is front-loaded and nothing is redundant.

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 still names what comes back (preview image plus vault asset id), and it covers the pre-build approval intent, credit behavior, and the reference-anchoring prerequisite. An agent has everything needed to sequence and invoke it 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 coverage is 100%, so baseline would be 3, but the description adds workflow meaning: seedImageAssetId comes from attach_influencer_reference and anchors identity to the user's own photo. That is value beyond the schema's field-level descriptions.

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 precise verb+resource ('generate a single cheap look preview portrait for an influencer') and explicitly scopes it as a pre-approval step distinct from the full vault build. Repeating that the vault later seeds from this look makes the tool's role unmistakable.

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?

Explicitly says to use it BEFORE the full vault build so the user can approve the face, and gives a concrete prerequisite chain: call attach_influencer_reference first, then pass its returned asset id as seedImageAssetId. Both when-to-use and the alternative (vault build) are named.

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