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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior: it is paginated, searchable with contains semantics, and requires a bearer token — auth needs are not in the annotations, so this earns credit above baseline.

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?

Three front-loaded clauses — purpose, pagination/search behavior, auth — with no filler. Every sentence carries information an agent can act on.

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 no output schema, the description should sketch the shape of an error row (row number, item ID/SKU, reason). It names 'reason' only, leaving the per-row payload largely unspecified, and gives no guidance on paging through large error sets.

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 50%: 'id' and 'search' are documented in the schema, while 'page' and 'limit' are bare. The description's mention of pagination and search-by-item-ID-or-SKU only restates what the schema already says and adds no defaults, ranges, or page/limit guidance.

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 and resource ('List per-row errors for a CSV import') plus the payload ('rejected rows with reason'). This is clearly distinct from siblings like get-import-csv (import status) and retry-import-rows (remediation), so an agent can route without opening the 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?

Implies context via 'rejected rows' and mentions the search-by-ID/SKU affordance, but never states when to call this versus get-import-csv or retry-import-rows, and gives no prerequisites or exclusions.

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