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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description's one genuine addition is the authentication model — local WordPress auth, no REST API keys — which is real context an agent can act on. It adds nothing about result ordering, default sort, or how far pagination can go beyond the schema's own max.

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, front-loaded with purpose and followed by the operational caveat about authentication. The reference to the upstream method name `get_orders` in woocommerce-mcp-server is only marginally useful to a calling agent, but it is contained in the same sentence that delivers the auth benefit.

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 free-form `filters` object accepts arbitrary WooCommerce REST API filter keys with no examples anywhere, and there is no output schema to describe the return shape, so an agent gets no help constructing meaningful queries. For a list tool with a nested open-ended parameter and no output contract, the description should sketch at least a couple of common filters and the response envelope.

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 100%, so page, perPage, filters and site_id are already documented, including the instruction to call list_sites first for site_id. The description only restates that pagination and filters exist, adding no filter-key examples or syntax beyond what the schema provides. Baseline 3 applies since the schema carries the load.

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?

"Retrieves WooCommerce orders with pagination and filters" states a specific verb (retrieves) and resource (orders) and signals batch/list semantics via pagination, which implicitly separates it from the singular wc_get_order. It never names that sibling explicitly, so an agent must infer the plural-vs-singular split from the tool name alone.

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?

Usage is implied rather than stated: 'with pagination and filters' tells the agent this is for browsing collections, and the auth note removes a common blocker. There is no explicit when-to-use / when-not-to-use guidance and no pointer to wc_get_order for a single order or to the report siblings for aggregates.

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