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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description adds valuable behavioral constraints beyond annotations: preserving job IDs, draftJobId semantics for Seedance Draft steps, expiry eligibility, and delivery via present_generation. It does not cover pagination behavior, but the added context is substantial.

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 key usage scenario and scope are front-loaded, and most sentences carry important guidance. There is some redundancy (get_generation_status is mentioned twice) and the description could be tightened, but it is not bloated.

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 no output schema and four parameters at 0% schema description coverage, the description should explain what a page contains, how pagination works, and what each filter does. It leaves significant gaps around status filtering, limit behavior, and cursor usage, making it incomplete for an agent to use the tool confidently without inspecting the schema.

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 must compensate, yet it only explains the surface filter ('video, image or audio when known'). It does not explain the status enum (accepted/running/completed/failed), the default limit of 10, the maximum of 20, or the cursor for pagination; 'bounded page' hints at limit/cursor but provides no usable semantics.

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: 'Recover a bounded page from the same connected user's MaxVideoAI library' with optional surface filtering. It explicitly distinguishes from siblings by naming get_generation_status for follow-up and present_generation for delivery, and warns against using it to generate, retry, or charge.

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?

It clearly states when to use (lost job identifier or submission response, user returns to recent work) and when not to use (do not claim completion for accepted/running jobs, do not use to generate/retry/charge). It also directs to get_generation_status for follow-up and present_generation for completed results.

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