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

Annotations already mark this as read-only and non-destructive, but the description adds important behavior beyond that: per-response options are read at collection time rather than at queue time, a job can be collected with more detail without a second browser run, and no page is loaded or charged.

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 first sentence front-loads the critical routing information, and every following sentence contributes non-obvious behavioral detail. There is no wasted prose; the description is dense but well organized.

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 covers trigger conditions, polling behavior, response equivalence, collection-time option semantics, and cost/charge implications. Because the payload is stated to be identical to the queued tool's inline result, the absence of an output schema is not a gap.

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 fully documents all six parameters with a 100% coverage, so the baseline is 3. The description adds meaning by explaining the jobId contract and clarifying that the boolean per-response options are evaluated when the job is collected, which gives the agent a better mental model of how the parameters work.

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 and resource: collect the stored result of a queued job. It names the exact four tools that can return a job id and clearly distinguishes this tool from inline result delivery.

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 explicitly says when to use the tool: when keyboard_walk, simulate_condition, screen_reader_transcript, or check_page_alt_text returned a job id instead of a result. It also tells the agent to retry after a few seconds if the job is still running and explains that no different parsing is needed because the payload is identical to inline.

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