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 adds genuinely useful behavior beyond them: rows appear with no BillID, and the tool never fans out across Locations and will require a single Location when several exist. However it says nothing about pagination/limit behavior or how many checks a search may return, which matters for an openWorld read.

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?

The purpose and the when-to-use case are front-loaded in the first two paragraphs, and the location caveat comes last where it belongs. Slightly verbose with the multi-line formatting and redundant restatement that download_invoices cannot reach these rows, but every sentence still carries information.

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?

End-to-end workflow is covered: search by date/payee/amount, then hand the FileID to download_attachment. An output schema exists so return values need no explanation. The gap is the undocumented filter parameters (limit, check_id) and date format for a 7-parameter 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 description coverage is 0% across 7 parameters, so the description carries the burden. It meaningfully explains the search axes (date range, payee, amount) and gives a strong semantic for location (single Location ID, required when multiple Locations exist, see list_locations). But limit, check_id, and the start_date/end_date format are entirely unexplained, leaving roughly half the surface ambiguous.

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?

Specific verb (List) plus precise resource (invoice scans attached to checks, with their FileIDs) and an explicit statement of the data gap it fills: scans that hang off the check with no BillID. It names the siblings get_bills and download_invoices as unable to reach these rows, so an agent can distinguish it without opening any schema.

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?

States exactly when to reach for this tool (vendor paid by check with no AP bill record) versus the alternatives, and what to do next: pass the FileID to download_attachment to read the document. It also spells out the location prerequisite and the no-fan-out constraint, plus a pointer to list_locations.

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