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

Annotations already establish this is a read-only, closed-world operation. The description adds genuine behavioral context beyond them: this tool blocks and loops until a terminal state, rather than returning a single snapshot. It stops short of disclosing timing behavior, defaults, or the cost of long polls.

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?

One front-loaded sentence: verb and behavior come first, and the generator list is a compact clause rather than padding. Slightly list-heavy, but every element is load-bearing.

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 0% parameter coverage, the description should at least say what a completed poll returns or how the wait is bounded. It gives terminal states but nothing about return payload (URL/asset id), timing bounds, or how maxAttempts/intervalSeconds shape the wait.

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% and the three parameters (generationId, maxAttempts, intervalSeconds) are entirely undocumented in both schema and description. The word 'Poll' faintly implies interval/attempt semantics, but there is no statement of what maxAttempts or intervalSeconds mean, their units, or defaults.

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 ('a video job') with clear terminal outcomes (COMPLETED or FAILED), and enumerates the five generator tools whose jobs it watches. It does not explicitly contrast itself with the sibling video_status, so an agent must infer the difference between blocking poll and simple status read.

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?

The list of generator tools implies 'call this after create_video/upscale_video/etc.', which is real routing guidance. However, it never says when NOT to use it or names the non-blocking alternatives (video_status, wait_for_clipping, wait_for_image) that a sibling-aware agent would want ruled out.

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