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

Annotations already declare the mutating, open-world, non-idempotent, non-destructive profile, so the description doesn't need to repeat safety. It adds genuinely new behavior: a 2-minute input cap, a 1-credit charge, and the asynchronous pattern (poll list_creations), plus the schema notes the remote file is "downloaded once." Failure/error handling and whether a new creation is produced are not stated.

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?

Two sentences, front-loaded with the core action and options, then the cost and the polling instruction. No filler or restatement of the title.

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 3-param async mutation with no output schema, the description covers input limits, cost, which result list to poll, and the fit/aspect semantics. It lacks any note on what happens on failure or whether the original video is preserved, which are the remaining ambiguities for an agent planning a call.

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 67% and the one undocumented parameter is `fit`; the description covers exactly that gap by explaining the two modes as "filling the frame or on a blurred background." The `video` and `aspect` params are already well documented in the schema, so the description adds value where it was missing rather than duplicating.

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 a specific verb and resource ("Re-cut a video ... to another frame") plus the exact supported frame ratios and the two background treatments. This makes it unmistakable against siblings like create_video or generate_clips, which produce new footage rather than re-framing existing footage.

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 concrete operating context: max 2 minutes of source video, cost of 1 credit, and the follow-up step "Poll list_creations" to retrieve the result. It does not name an alternative tool or state when-not to use it (e.g. for videos over 2 minutes or for generating rather than reframing), so it stops short of full routing guidance.

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