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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds substantially more: a 24 MB size cap, no resizing ("kept at its own size"), link-sharing requirements, and the fact that it is free. It also discloses the asynchronous job pattern — returns job_id, poll job_status, then read clip_ids — which is behavioral information absent from the annotations and critical to correct use.

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 trigger, then parameter definitions, then the return/polling path, then exclusions — a sensible ordering with no filler sentences. It reads as one dense block rather than being line-broken, which costs a little scannability, but every sentence adds information an agent needs.

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 two-parameter async import tool, the description covers the trigger, both input forms, size constraints, the polling handoff to job_status, the downstream tools that consume the resulting clip id, and explicit exclusions. An output schema exists, yet the description still gives the job_id → clip_ids flow, which is what the agent actually needs to chain calls.

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 description coverage is 0%, so the description carries the full burden, and it does: url is a direct https link to .jpg/.png/.webp or a publicly-open Google Drive, Dropbox or OneDrive share link; file is a user attachment passed through the assistant's file mechanism. That is materially more than the bare string/$ref types the schema provides.

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 — bringing a photo into RipClip to edit it — and grounds it in concrete user utterances ("brighten this photo", "fix the colors on this image"). It explicitly separates itself from import_video and from photos already in the library, so an agent can distinguish it from siblings without opening a schema.

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?

Opens with the trigger condition ("Use this when the user wants a photo brought into RipClip to edit it") and closes with a "Not for:" block naming the correct alternatives: import_video for videos, list_clips kind photo for existing photos, and an out-of-scope case. Both the when-to-use and when-not-to-use conditions are explicit.

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