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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds genuinely useful behavior: result ordering (newest first), row typing, and the absence of a total count with a concrete pagination termination rule ('keep paging until a page returns fewer rows than asked for'). It does not mention default page size, but the schema covers that.

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 core differentiator and free of filler, but five sentences is on the long side and the three quoted example questions plus 'the same list the customer screen shows' are partly rhetorical padding.

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?

There is no output schema, yet the description compensates by describing the return shape (rows typed order/refund, newest first, no total count) and the paging contract. Nothing needed to call and consume this tool correctly is missing.

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 all three parameters are already documented, including the 'not a name' note on customerId, which the description merely repeats. The pagination guidance adds marginal meaning but no new parameter-level syntax. Baseline 3 is correct.

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 with precise scope: one customer's merged order+refund timeline, newest first, with row type markers. It explicitly distinguishes itself from hub_get_orders and hub_get_refunds, so an agent can route without opening either 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?

Gives an explicit alternative and the exact condition that selects this tool: 'get_orders with customerIds returns the orders alone and a total count; use this tool when the refunds belong in the answer.' It also states the ID must come from get_customers and never a name, which is a real invocation constraint.

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