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

Annotations already establish readOnly, idempotent, non-destructive behavior, so those need not be restated. The description adds genuine value beyond them: it explains that description is 'what every render follows', that a null reference_image means 'not rendered', and that voice_id exists only for characters.

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?

Three compact lines that front-load the resource and then enumerate the returned fields. Every clause carries information; no filler. Slightly dense phrasing, but appropriately sized.

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?

With no output schema, the description carries the return-shape burden and does so well, naming the fields each asset returns and their meaning. For a simple two-parameter read tool this is sufficient for an agent to call and interpret it correctly.

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 100%, so project_id and asset_type are already documented by the schema (including the 'Only this kind' filter). The description echoes the three asset kinds but adds no syntax or filtering detail beyond what the schema provides, so the baseline 3 applies.

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 identifies the resource (the project's characters, environments and objects) and what each carries, and combined with the name/title it is clearly the read operation. It does not explicitly name that it reads versus its siblings (assets_edit, assets_generate), but the returned-field detail makes the purpose unmistakable.

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?

There is no explicit when-to-use versus assets_generate or assets_edit, but the parenthetical 'reference_image (null: not rendered; view_image it)' routes the agent to a sibling tool conditionally. The closing domain rule ('Each needs a reference image before the voiceover') hints at when this data matters but is not framed as usage guidance.

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