review_import

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

Annotations already declare readOnlyHint=true, and the description's 'Return' aligns with that. The description adds that it returns staged candidates and statuses per batch, which is useful scoping, but it does not disclose behavior such as error handling for unknown batch IDs, possible empty results, or whether statuses follow a particular workflow.

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 description is a single front-loaded sentence with no wasted words. Every term contributes: 'Return' states the action, 'staged candidates and statuses' states the output, and 'one batch' states the scope. This is an appropriately sized definition for a simple single-parameter tool.

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?

For a read-only tool with one parameter and an output schema, the description covers the essential behavior: what it returns and for what scope. It is complete enough to call correctly with a valid batch_id. The main missing piece is linkage to the staging workflow, but the output schema and annotations cover return values and safety.

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?

There is one required parameter, batch_id, and schema description coverage is 0%. The description only says 'one batch,' which adds minimal conceptual meaning but does not explain where batch_id comes from, what format it takes, or how it relates to stage_candidates. Given the low schema coverage, the description should compensate more but does not.

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 uses a specific verb ('Return') and names a clear resource ('staged candidates and statuses') scoped to 'one batch.' This clearly differentiates it from sibling staging and commit tools like stage_candidates and commit_import, which involve different stages of the import flow.

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?

The description implies this is the tool to inspect previously staged candidates for a specific batch, but it does not explicitly say when to use it versus stage_candidates or commit_import. It also does not state that a batch must already exist or have been staged before calling, which is useful context for correct usage.

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