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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that with the blocking wait behavior, the one-hour timeout failure mode, and the 'Requires an active Revid plan' prerequisite, but it omits rate-limit or backoff guidance for the repeated polling it explicitly recommends.

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?

The description front-loads the trigger condition and keeps every sentence informative: statuses, retry behavior, timing expectations, and plan requirement all inform the call. It is dense but well ordered; the latency-range sentence is borderline but justifies waitSeconds choices.

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?

With an output schema present, the description does not need to enumerate return fields, yet it still explains the meaningful status states and the failure path. The only gap against a two-parameter polling tool is guidance on polling cadence or how many retries are reasonable before giving up.

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 both parameters are documented structurally. The description still adds meaning the schema lacks: the default of 40 seconds and the operational consequence of a 0 value ('0 checks once'), plus the realistic latency ranges for images versus videos that inform how an agent should set waitSeconds.

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?

The description states a specific action tied to a specific resource: poll the status of media created by `generate_media` using its mediaIds. It explicitly distinguishes itself from the sibling generator tool by describing the follow-up role, so an agent knows this is the completion-check step, not the creation step.

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?

Usage is fully prescribed: call it after `generate_media` returns "processing", pass that call's mediaIds, and if the result is still "processing", call again with the same ids. This is an explicit when-to-use plus a retry loop, leaving nothing to inference.

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