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

Annotations only cover the read-only/non-destructive surface; the description adds genuinely non-obvious behavior: XLSX returns base64 bytes with a content type, all rows pages for one file count as a single token use, a full download counts once each, and the token is bound to the current session. Those are quota and auth semantics an agent cannot infer elsewhere.

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 action and precondition, then formats, then quota/failure handling. Nearly every sentence carries distinct information, though the format enumeration is dense and could be tightened by grouping the extra.* variants.

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 does the heavy lifting on return format for XLSX and for the rows/fields pages, and covers quota, session binding, and token refresh. It is slightly thin on what the plain list and rows responses actually contain and on offset/limit paging semantics.

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 20% (only order_id is documented), so the description must compensate; it does by mapping every enum value to a meaning (list vs rows vs json/csv/xlsx, plus the paid excess-rows extra.* variants) and flagging the base64 encoding for XLSX. However, limit and offset paging parameters are never explained, leaving two of five parameters undocumented in both places.

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 concrete verb+resource pair: list files or read rows for a paid order using a delivery token. It also enumerates the output formats (json, csv, xlsx, fields.json, extra.*) so the agent knows exactly the kind of content this returns, which distinguishes it from get_order and get_payment_status in the sibling set.

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 precondition ("After payment"), an explicit failure branch ("On expiry or download_limit, call get_order with your order capability for a fresh token"), and a recovery path when the session itself is gone (initialize a new session, then get_order). The alternative tool is named, not implied.

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