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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantial behavior beyond them: the preview/Full-Review tiering, the 'processing' status with check_again_after_seconds polling, and an instruction not to invent critique or fixes when reporting. The only gap is that it never states whether a Full Review costs quota or requires an entitlement check, which is implied by 'if the account has one' but not explained.

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?

Front-loaded with the purpose, then the polling rule, then the reporting constraint, then the exclusion — a sensible order with no filler sentences. It is somewhat dense, packing four distinct obligations into one paragraph, but every clause carries operational meaning.

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 tool is a single-parameter read with an output schema, so return-value documentation is unnecessary; the description nonetheless explains the preview.status field and the 'processing' vs 'ready' branches, which is exactly the context an agent needs to drive the polling loop correctly.

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 there is a single parameter, so the schema already carries the type and length bounds. The description adds real value by specifying provenance constraints on review_id (must come from a sibling tool and must be user-referred) plus that the same ID is reused across polling calls.

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 verb ('read') and resource ('preview, and the Full Review') for a review_id, and explicitly scopes the source of that ID to review_manuscript or list_manuscript_reviews. An agent can distinguish this from the sibling list_manuscript_reviews (which enumerates) and review_manuscript (which creates) without opening any schema.

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 gives an explicit positive trigger (review_ids returned by the two sibling tools), an explicit exclusion ('Do not use it for review_ids the user has not referred to'), and a concrete retry procedure for the processing state. Nothing about when to call versus call again is left to inference.

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