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

readOnlyHint/openWorldHint/destructiveHint already declare the safety profile, so the bar is lower. The description still adds real behavioral value by disclosing that results are full records carrying SyncToken, meaning no follow-up fetch is required — a non-obvious trait beyond the annotations or schema.

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 tight sentences that lead with the core action and follow with the highest-value behavioral fact (full records, no get needed) and a usage tip. No filler sentences.

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?

No output schema exists, yet the description notes results are full records with SyncToken, covering the main return concern. The criteria param carries extensive pagination/filter documentation in the schema, so the description is largely complete, though it never restates the 1000-record/offset paging limit that an agent will hit.

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 100%, so the baseline is 3. The description goes slightly beyond it by showing a concrete criteria pattern ('Id IN' for batch reads) and explaining the record completeness that criteria results return, which a reader would not infer purely from the generic property schema.

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 ('Search sales receipt records in QuickBooks Online'), which cleanly separates it from search_invoices, search_refund_receipts and the other search_* siblings by resource. It does not explicitly name the sibling it replaces for single-record fetches, but the scope is unambiguous.

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?

'no get is needed after' implicitly steers the agent away from get_sales_receipt, and 'read several known Ids in one search with Id IN' gives one concrete use case. However, there is no explicit when-to-use vs when-not statement or named alternative, so guidance is implied rather than spelled out.

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