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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral value beyond that: results are a bounded page with a total rather than a full export. It stops short of explaining pagination bounds or ordering semantics, which are only implicit in the 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 with zero filler: the filter inventory comes first, followed by the return-shape constraint. Nothing repeats the schema or the annotations verbatim.

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?

For a tool with roughly twenty filter parameters, no output schema, and no per-parameter docs, the description adequately covers the primary filter axes and the return shape. However, it omits the pagination/sorting behavior and several non-obvious flags (outstanding, document_type, po_match), leaving an agent to discover them from the raw schema.

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 0%, so the description must carry the load. It does name most filter families (client, vendor, date, review, due, duplicates, amount), mapping them to the corresponding parameters, but leaves limit/offset, sort_by/sort_order, outstanding, document_type, po_match and validation_status entirely unexplained.

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 ("Find saved invoices") and enumerates the filter dimensions covered (client, supplier, date, review, due-date, duplicate, amount). It does not distinguish itself from sibling search tools such as search_documents, get_spend_invoices, or list_trashed_invoices, so an agent must infer that this one is scoped to saved, non-trashed invoices.

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?

"Return a bounded page and total, not an export" implicitly steers away from export_saved_invoice / invoice_to_excel, which is a useful negative cue. But there is no explicit when-to-use guidance versus search_documents, get_spend_invoices, or get_review_queue, all of which plausibly overlap with invoice listing.

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