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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=false), and the description adds meaningful extra context: 10–30 minute render latency, asynchronous completion surfaces, and determinism when inputs repeat. It does not spell out failure modes for oversized/invalid photos or what happens when the account lacks 1080p, which are the remaining behavioral gaps.

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 triggering condition and the core transformation; every clause (latency, determinism, exclusions) carries information. It is a single dense paragraph, though, so the timing and exclusion facts compete for attention rather than being visually separated.

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?

Given an output schema exists, the description needn't explain return values, and the remaining complexity — a long-running async render with 11 parameters — is covered by the latency window, the update surfaces, and the pointer to get_video_status. An agent has everything needed to call it and set expectations for the user.

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; the description still adds framing value by naming which text fields land on the opening card, closing card, and captions, and by stating the 1–8 photo range and MP4 output shape. It does not clarify ordering semantics or default behavior beyond what individual schema descriptions already say.

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 concrete verb and artifact ('Turns 1–8 uploaded photos into a polished 16:9 MP4') and enumerates the exact request types it serves: listing video, property tour slideshow, just-listed/open-house video, social/MLS slideshow. It also explicitly excludes text-prompt video generation and video editing, which no sibling covers, so an agent can route correctly without opening the 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 an explicit trigger ('Use this when the user wants a video made from photos') and closes with explicit non-triggers ('Not for generating video from a text prompt alone, for chatbots, or for editing existing videos'). It also names the follow-up tool, get_video_status, and the surface (ChatGPT video card, Agent One page) where results appear.

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