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

Annotations already establish readOnlyHint=true, so the safety profile is covered. The description adds two behavioral details beyond annotations: returned ref ids can be fed to generate_video, and the operation is 'Free' (no credit cost). It does not address output shape or pagination, but for a read-only list with annotation coverage, this is adequate, not rich.

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 short, but brevity comes at the cost of substance: the main phrase duplicates the title and leaves no room for purpose or parameter detail. It is under-specified rather than efficiently concise.

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 1-parameter read-only list without an output schema, the description is minimally serviceable but fails to fully situate the call: it omits what the response contains (beyond id semantics), how kind filters results, and how this differs from sibling list tools. The generate_video reference hint is useful, but it is one dangling detail rather than a complete picture.

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?

With 0% schema description coverage, the description needed to compensate by explaining the kind parameter, but it never names kind. 'Characters, props, places' maps loosely to three of the four enum values and omits 'look', and it offers no definitions or guidance for choosing a value.

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's primary clause 'Characters, props, places' exactly restates the tool title and leaves the verb implicit; an agent must infer 'list' from the tool name. The added phrase about ref ids is data semantics, not a statement of purpose, and it does not distinguish this listing tool from siblings like list_assets or list_generations.

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?

No explicit when-to-use guidance or comparison to alternatives is given. 'ref ids are generate_video reference_image_ids' hints at a downstream use in generate_video, but it does not say when to prefer list_entities over list_assets, get_entity, or other siblings. The word 'Free' vaguely signals cost, but not usage conditions.

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