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

Beyond the annotations (which only declare it as a non-readonly, non-destructive, non-idempotent, closed-world write), the description discloses the 20-characters-per-project quota and the side effect that use_in_videos makes this character apply to the next videos. It does not say what is returned on success, which matters somewhat given there is no output schema.

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?

Two dense sentences, front-loaded with the verb and resource, then the two input modes, then limits and the use_in_videos side effect. The telegraphic phrasing ('character_fields (get_catalog)') is efficient rather than wasteful, though it reads a bit compressed.

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 5-parameter mutation with a nested object and no output schema, the description covers input modes and quotas but leaves gaps: no return value, no indication of whether project is required or defaulted, and no note on name constraints beyond the schema's maxLength.

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 40%; the nested look subobject is thoroughly enumerated but name, project, and use_in_videos carry no schema descriptions. The description compensates partly by pointing at get_catalog for character_fields/character_presets and explaining that look fields override a preset, and it explains use_in_videos, but 'name' and 'project' semantics remain unstated.

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 — creating an AI character for the project's videos — and scopes it to a 'look' being either a full field set or a preset. The 'from a look' framing implicitly separates it from create_character_from_photo, but no sibling is named explicitly.

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 clear usage context: two input paths (full look via character_fields from get_catalog, or a preset name with overrides), a hard cap of 20 per project, and the effect of use_in_videos. It stops short of explicit exclusions such as when to prefer create_character_from_photo or update_character instead.

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