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

Annotations already flag this as a destructive, idempotent write, and the description adds meaningful behavior on top: passing an empty provider clears the voice, and account_uuid must be the UUID, never the numeric id. It does not state permission requirements or whether the prior voice is lost on overwrite, which is the main remaining gap.

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?

The purpose is front-loaded in the first clause, then parameters are laid out in a single semicolon-delimited sequence with no filler. It is dense enough that a reader must parse carefully, but 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?

For a five-parameter mutation with no output schema and nested-ish traits, the description covers inputs, provider rules, clearing semantics, and the downstream effect on UGC/film rendering. It stops short of documenting failure modes (unknown character, invalid voice for the chosen provider) or what the tool returns after setting.

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 0%, so the description carries the full burden and largely succeeds: it enumerates provider values, explains account_uuid's format and provider dependency, states voice's per-provider requiredness, and lists all nine trait keys. Only character_uuid is left to its self-evident name, and the discovery pointer to list_voices_ai_accounts removes the trial-and-error that the schema would otherwise force.

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: give a character the voice it speaks with in videos. This is clearly distinct from neighbors like set_character_main_asset or set_social_account_character, and the scope ('in videos', tied to ugc_voice.character_voices) pins down exactly what is being configured.

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 real routing guidance: use list_voices_ai_accounts to discover accounts/models/voices, account_uuid is required for every provider but local, voice is required for elevenlabs but optional for local/openai. It also explains when the setting takes effect (when ugc_voice.character_voices names it as `character`). It lacks an explicit 'use edit_character instead if...' exclusion, so it falls short of a 5.

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