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

With no annotations, the description carries the full burden and provides useful behavioral context: it polls until a terminal state and backs off on HTTP 502. It does not disclose handling of other error types or what occurs when max_polls is exhausted, but these are secondary for a poll 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?

Two sentences with no filler. The first sentence states the core purpose and terminal condition; the second adds a valuable retry behavior. Every word contributes to the agent's understanding.

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?

The description is adequate for a simple poll loop: it states purpose, terminal conditions, and one error-handling behavior, with parameter defaults in the schema. However, it omits what 'delivered' or 'failed' map to in the response, behavior when max_polls runs out, and there is no output schema to explain return values. These gaps matter for an agent deciding whether this is the right tool.

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 67%; max_polls and interval_ms already have descriptions. The description's 'Poll ... until ...' implies queue_id identifies the video retrieve operation, which adds some context to the undocumented parameter, but it does not fully compensate for the missing queue_id 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 ('Poll video retrieve') and a terminal condition ('until delivered or failed'). It clearly implies the tool waits on the video retrieval process, distinguishing it from the direct video_retrieve sibling, though it doesn't explicitly name the alternative.

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 implied: the agent should call this when it wants to wait for a previously requested video retrieval to finish. However, there is no explicit guidance on when to prefer this over direct polling of video_retrieve or other siblings, and no exclusions or alternatives are named.

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