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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that these are *finished* videos and how a post consumes the output url, but says nothing about pagination behavior, ordering, or result size limits.

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?

A single tight sentence with the read tag front-loaded and the returned fields enumerated early. No waste, though the bracketed '[read]' is redundant with readOnlyHint.

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?

Naming the returned fields partially compensates for the absent output schema, but with two undocumented pagination parameters and no ordering or size information, an agent cannot confidently page through results.

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% for both `page` and `per_page` — the schema gives only types and defaults, no semantics. The description never mentions them, so an agent gets no explanation of paging or per_page limits, failing the low-coverage compensation requirement.

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 the resource specifically ('The merchant's finished videos') and enumerates the fields returned (video_id, video_uuid, title, output url), which separates it from list_images and list_tt_videos. The verb 'list' is implicit rather than stated, slight ding, but the object is unambiguous.

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?

'Use one instead of making a new video when it fits the topic' gives a genuine reuse cue, but there is no guidance on when to pick this over sibling listers like list_tt_videos or list_agent_office_films, and no mention of pagination or when the list is empty.

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