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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral value by exposing the job's outcome states (succeeded/failed) and the required follow-up action for each; it stops short of describing polling cadence or result contents.

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, outcome-first structure, zero filler; the primary action ('Poll a queued...') is front-loaded and the branching follows immediately.

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?

An output schema exists so return values need not be explained, and the workflow guidance is present. However, for a 3-parameter polling tool it omits the origin of job_id and any guidance on repeated polling or job expiry, leaving a real 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?

Schema description coverage is only 33% — only organization_id is documented, and job_id/study_id are bare UUIDs. The description never mentions any parameter, so it does not compensate by explaining that job_id comes from queue_customize_study or why study_id is needed alongside it.

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 a specific resource (a queued study customization job/turn), which is clearly distinct from the queueing sibling queue_customize_study and from get_study. It does not explicitly name the sibling it complements at the queueing stage, so it falls just short of full differentiation.

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?

Gives concrete next steps conditioned on outcome: on succeeded, inspect result and call get_study; on failed, inspect the saved study before retrying. That is a clear usage contract, though it never says when not to poll or how often to poll.

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