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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely non-obvious behaviour: each call in a card client draws another card, and the call costs no credits. It does not repeat the annotation claims. Only gap is no statement about rate limits or error/not-found behaviour.

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?

Front-loaded with the resource and status set, then the routing/polling rules; every sentence carries distinct operational information. It is dense and slightly long, but nothing is filler.

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?

An output schema exists so return structure need not be explained, yet the description still flags the playable url on completion and the terminal states. Combined with the polling guidance, an agent has everything needed to call this correctly in either client type.

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 baseline is 3, but the description adds real meaning the schema lacks: which id each kind expects and where it comes from (create_clip for clip, make_video for video, approve_episode for episode), plus the default kind.

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?

Names a specific verb+resource (status of a clip/video/episode) and enumerates the three kinds with the source of each id, so it is immediately distinguishable from siblings like list_videos or create_clip. The status vocabulary (pending, processing, completed, failed) further pins down what is being fetched.

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 explicit when-to-use ('Call it when the user asks to see or check a video') and, unusually, an explicit when-NOT-to-poll rule for card clients plus the alternative behaviour for terminal clients (poll ~10s). This is routing guidance an agent cannot infer from the schema.

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