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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so the safety profile is covered. The description adds genuinely useful behavior: a bounded wait of about 20 seconds and the two possible outcomes (assets returned vs. still running). It stops short of saying whether to poll again or how many retries are sensible, which is the key operational unknown for a wait-style 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?

One sentence, front-loaded with the trigger condition and followed by the outcome envelope. No filler, no redundancy.

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 one parameter, no output schema, and simple annotations, the description covers the main gaps: the trigger, the wait, and what comes back. It leaves the retry/polling protocol and any failure modes unaddressed, which is a minor but real omission for a tool that can return "still running."

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% and the single run_id parameter is already documented in the schema as coming from a "Still generating" response. The description restates that same origin without adding format, validity-window, or cross-run constraints, so baseline 3 applies.

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 pairs a specific verb ("Collect") with a specific resource (a generation) and a precise precondition: the generation answered "Still generating." That scoping makes it clearly distinct from generic siblings like get_asset, though it never names an alternative sibling explicitly.

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 tells the agent exactly when to reach for this tool: after a generation response reports "Still generating." It does not spell out when not to use it (e.g., once a run is complete, prefer get_asset), leaving that to inference.

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