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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds real value beyond them: no automatic pagination, no retries, and concrete rate-limit ceilings. It omits what happens when page exceeds available data, but the added operational context is substantial.

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?

Four short sentences, front-loaded with what is returned before any operational caveats. Each sentence carries distinct information (scope, expressions, paging, rate limits) with no filler, though the phrase 'up to 100 receipt lines' is slightly ambiguous against the limit parameter.

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 still conveys return shape (a page of ASNs plus receipt lines), the full_page continuation signal, and the absence of automatic retries or pagination. For a read-only search tool with four optional parameters, that covers everything an agent needs before calling it.

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%: sort and filter already carry their own descriptions, and the prose adds only the 'optional Infoplus filter and sort expressions' framing. The page and limit parameters are undocumented in both schema and description, so defaults and paging arithmetic remain unstated. Baseline 3 fits when the schema does half the work.

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 gives a concrete verb and resource ('Read one page of advance shipping notices') plus the scope of included receipt lines, which is far more than the title alone. It does not explicitly contrast itself with infoplus_get_asn, so the single-record vs. paged-list distinction is left implicit for the agent to infer from 'search' vs 'get'.

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?

It states the operational conditions clearly: request the next page when a result is full_page, and pace calls within 3/second per user and 10/second site-wide. It stops short of naming infoplus_get_asn as the alternative when a single known ASN is wanted, so the routing guidance is incomplete.

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