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

Annotations only declare the non-read-only, non-destructive, non-idempotent profile. The description adds real behavioral context not present in structured fields: creation is private with public embedding disabled, no call is started, and concrete Anima defaults (fast mode, square orientation, visual stability 0.81, motion freedom 0.95) are disclosed. Missing only error/idempotency behavior.

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?

Five short sentences with the purpose front-loaded, followed by defaults, privacy behavior and the next step. Dense and largely waste-free, though the closing 'Prepare the returned character ID next' is slightly clipped in phrasing.

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 18-parameter mutating creator with no output schema and an entirely undocumented schema, the description does well on behavior (privacy, no-call, defaults, follow-up) but never addresses how the response is shaped or which required fields demand care. Adequate, with clear gaps.

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 0% across 18 parameters, so the description carries the entire burden, and it only partially pays it: it disambiguates image vs voice source and supplies defaults for animaMode, orientation and the animation settings. Required inputs such as name, systemPrompt and workspaceId, plus cerebro, language, openingLines, knowledgeText and maxSessionSeconds, are never explained.

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: 'Save a real live conversational avatar draft' from an image plus a catalog or custom voice. The 'draft' framing and 'Does not start a call' make it distinguishable from session tools. It never names or contrasts with update_live_avatar or prepare_live_avatar, so sibling differentiation is incomplete.

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 sequencing hints ('Does not start a call', 'Prepare the returned character ID next'), which tells the agent where this sits in the avatar flow. However, it does not state when to choose this over prepare_live_avatar or update_live_avatar, and no prerequisites are called out. Usage is implied rather than explicit.

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