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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations: it explains that a null reference_image means the asset has not rendered, that image status can be 'stale' after description changes, and that characters include a voice_id. It does not cover pagination or auth, but the bar is lower with annotations present.

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 description is a single dense but efficient sentence that front-loads the core resource and packs useful field semantics into parentheticals. It is appropriately sized, though the nested clauses make it slightly harder to scan.

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 burden of explaining return values, and it does so well: it names each field, explains null reference_image semantics, describes stale status behavior, and notes voice_id for characters. It also includes a prerequisite note about reference images before voiceover, leaving only minor gaps like pagination.

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 the schema fully documents both project_id and asset_type. The description mentions asset types but does not clarify that asset_type is an optional filter ('Only this kind'), so it adds little meaning beyond the schema. A baseline 3 is appropriate when schema descriptions are complete.

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 clearly specifies the resource being read (the project's characters, environments, and objects) and enumerates the returned fields. However, it lacks an explicit verb like 'list' or 'read' and does not directly distinguish itself from siblings such as assets_edit or assets_generate.

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?

It provides implied usage context: null reference_image means 'not rendered; view_image it' and every asset needs a reference image before voiceover. But it does not explicitly say when to use this tool versus alternatives like assets_edit or assets_generate, leaving core selection guidance to inference.

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