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

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, so the safety profile is covered. The description adds genuinely new behavior: it reads from the user's saved Puley history and consumes no read allowance, and find/sort_by apply across the whole saved table rather than just the returned page. It stops short of describing failure behavior for an invalid or expired cursor.

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 purpose and the cursor contract, then behavior, then filtering options — a logical order with no filler. The awkward line break mid-sentence and the parenthetical examples make it denser than it needs to be, but nothing is wasted.

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 correctly takes on the return contract (next rows or text plus another cursor until complete is true), which is what an agent needs to loop. The remaining gap is error/expiry handling for the cursor, minor for an idempotent read tool.

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 0%, so the description must carry all parameter meaning and it does: cursor is sourced from completeness.more.cursor, find matches rows containing every comma-separated term (AND semantics, shown with an example), sort_by orders by exactly one column with an example, and descending selects highest-first. This is meaning well beyond the bare schema titles.

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 next part of a Puley result that was too long for one answer" states a specific resource and the exact condition that makes this tool applicable (completeness.complete is false). No sibling tool in the list covers pagination of a saved result, so it is distinguishable, though the description never names the tool that produced the truncated answer (read/read_site/etc.) to close the loop.

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 gives an explicit trigger (completeness.complete is false) and tells the agent exactly where the required argument comes from (completeness.more.cursor from that answer), plus the loop condition (until complete is true). It does not state when NOT to use it — e.g. what to do if the cursor is stale or the result has expired.

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