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

Although no annotations are present, the description discloses that the tool repeatedly polls, stops on 'delivered or failed', and backs off on HTTP 502. This is useful, but it omits what happens when max_polls is exceeded or what the return value looks like, so the behavioral disclosure is only partial.

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?

Two short sentences with no filler; the main action and termination condition are front-loaded, and the backoff behavior earns its place as operational detail. This is appropriately sized for the tool's simplicity.

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?

For a simple polling tool with no output schema and no annotations, the description covers the core loop and a notable retry behavior, but it lacks a description of return values, timeout/limit behavior, and when to choose this over sibling tools. It is minimally viable but leaves several operational aspects implicit.

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?

The schema documents max_polls and interval_ms, and the phrase 'Poll video retrieve' connects queue_id to a retrieval request, but the description adds no explicit parameter meaning. The required queue_id remains only implicitly explained, and with 67% schema coverage the description does not go beyond the structured information.

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 uses a specific verb 'Poll' with a clear resource ('video retrieve') and terminal conditions ('delivered or failed'). It clearly distinguishes itself from one-shot retrieval siblings like video_retrieve by indicating a repeated polling loop, and the backoff note adds operational clarity.

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?

No explicit guidance is provided about when to use this tool versus alternatives such as video_retrieve or get_generation_status. The description implies its role as a waiting/blocking helper but does not state exclusions or preferred conditions, leaving the agent to infer usage.

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