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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuinely useful non-structured context: this is a blocking poll loop with defined terminal states and a return payload of clips with URLs. It omits polling budget/timeout behavior, which would matter to a caller of a blocking tool.

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?

Three sentences, front-loaded with the core action and terminal states, then the return value, then the usage caveat. No filler or repetition.

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?

No output schema exists, so the description compensates by stating what is returned (clips with output URLs), and it covers the blocking-poll semantics and the preview-panel exclusion. The main gap is the unexplained polling parameters, which leaves the caller unable to reason about attempt/interval tuning.

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% across three parameters, so the burden falls entirely on the description, which explains none of them. clippingId, maxAttempts, and intervalSeconds (with their bounds) are left for the agent to interpret solely from their names.

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 (poll) and resource (AI clipping job) with the terminal conditions (COMPLETED or FAILED) and the return value (clips with output URLs). It does not name or contrast with the adjacent sibling clipping_status, so an agent must infer the distinction between polling-to-completion and a single status check.

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 an explicit when-not ('Do NOT use this when the live preview panel is rendered') plus two when-to-use conditions (hosts without preview, or user asks for output URLs). It stops short of naming the alternative tool (clipping_status) to use otherwise, leaving that routing to inference.

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