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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the description correctly doesn't repeat the safety profile. It instead adds non-obvious behavior: results are paginated one page per call, and aggregate totals require the summarize.all_pages flag — a genuine behavioral trait the agent would otherwise discover by failing.

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?

Three short sentences, purpose first, then endpoint reference, then the pagination caveat. The API doc URL is mild filler but plausibly useful; nothing else 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?

An output schema exists, so return-shape explanation is unnecessary, and the pagination note covers the main trap. What's missing is disambiguation from the many voucher-related siblings and any hint about how the date/series filters interact with paging when computing totals.

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 79%, and the description only touches the nested summarize.all_pages parameter, explaining its purpose for the totals case. The many filter parameters (fromdate, todate, voucherseries, financialyear, expand, fields) are left entirely to the schema, which is acceptable at this coverage but adds no extra interpretation.

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 ("Retrieve all vouchers") plus the underlying endpoint, which lets an agent distinguish it from get_voucher (single record). It doesn't name the sibling directly, so differentiation is implicit rather than stated.

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 a real usage rule — one page per call, use summarize.all_pages when totals across all pages are needed — which is actionable. However, it never says when to prefer this over get_voucher, find_vouchers_without_attachments, or list-style siblings that filter vouchers, so routing is only partially resolved.

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