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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the description carries real behavioral burden – and it delivers cost ('a few credits'), latency ('ready in about a minute'), input constraints (≥480 px, upload_id origin), and a hard ordering dependency. What it omits is failure behavior (name collisions, generate-quota exhaustion), which keeps it short of a 5.

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 'Optional.' and the purpose, then the skip condition, then image sourcing, then ordering – a sensible priority order with no filler sentences. It is, however, one dense paragraph with heavy parenthetical nesting, which slightly impedes scanning.

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 mutation with a nested archetype object, no output schema, and 4 required fields, the description covers creation mode selection, prerequisites, cost, ordering, and kind semantics. It stops short of describing what is returned (e.g. the new subject's identifier used by later tagging) or error conditions.

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?

With only 50% schema description coverage, the description compensates almost fully: it explains the two mutually exclusive image routes (image_url vs upload_id), the generate flag's side effects and cost, and the critical conditional that archetype applies only to generate+person while description drives pets/objects. That conditional is not derivable from the schema alone.

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 ('Adds someone or something to the cast') and immediately bounds the scope relative to siblings: beyond the narrator and the product, i.e. not set_actor or set_product. It enumerates the three kinds (person/pet/object) and the mechanism (@[Name] tagging in moments), so the agent can distinguish it from add_moment without opening a 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 an explicit when-not ('Skip it unless the ad needs them'), names the prerequisite tool for the upload path (create_media_upload), specifies the generated path (generate: true), and states ordering constraints against add_moment and generate_script. Alternative routes for supplying the image are laid out as a decision, not left to inference.

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