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

With destructiveHint=true and readOnlyHint=false already declared, the description usefully adds patch semantics ("Preserves omitted settings, assets and publication status"), a preparation caveat, and an explicit non-goal ("Does not publish or start calls"). This goes beyond the annotations without contradicting them.

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 short, front-loaded sentences with no filler; the read-first instruction and preservation guarantee come first. Efficient, though they could be slightly more specific about the prerequisite.

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 a 19-parameter mutation tool with no output schema and nested objects, the description covers workflow and preservation but says almost nothing about the settings it edits. It's adequate for direction but incomplete for correct invocation across the parameter surface.

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 19 parameters including nested objects (cerebro, avatarAnimationSettings), so the schema provides no per-field meaning. The description only vaguely gestures at "image, voice or mode changes" and never explains the many settings, so it fails to compensate for the coverage 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?

The description states a specific verb+resource ("update") on an existing live avatar and adds a read-first workflow, making it distinguishable from create_live_avatar and get_live_avatar. It also rules out publishing or starting calls, which separates it from start_live_avatar_session. It's clear but doesn't explicitly name which sibling to prefer.

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?

"Read the existing avatar first, then update only requested settings" implies a workflow, and "Does not publish or start calls" sets scope. However, "may require preparation" only hints at prepare_live_avatar/get_live_avatar_readiness without naming them or stating conditions, leaving the prerequisite chain to inference.

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