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

Annotations already declare read-only, idempotent, non-destructive, closed-world semantics, so the safety profile is covered. The description adds the meaningful scope constraint ('unshipped'), but says nothing about ordering, default page size of 25, or that results cap at 100 — an agent could silently miss orders. No contradiction with openWorldHint=false, since 'connected store integrations' is a bounded set.

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?

A single short sentence with no waste, but brevity here comes from under-specification rather than tight editing. It is front-loaded, though the payload is thin.

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 must convey what a returned order looks like, how results are ordered, and how pagination behaves — none of which appear. For a listing tool whose defaults silently truncate at 25 records, this leaves real gaps.

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 only 50%, and the description contributes nothing about any of the four parameters — not what 'search' matches, not what 'ignored' switches to, not pagination behavior. The 'Import grid' analogy adds no operational meaning beyond what the schema already says for search and ignored.

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 identifies the resource ('unshipped orders from your connected store integrations') but is a bare noun phrase with no verb and leans on a UI reference ('as in the Import grid') that an agent cannot resolve. It does hint at scope (unshipped, i.e., not yet fulfilled) which separates it somewhat from list_shipments, but nothing explicitly marks the distinction.

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?

There is no statement of when to use this versus sync_store_orders, list_shipments, ignore_orders, or export_report, all of which sit in the same space. An agent must guess which retrieval path is appropriate.

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