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

Annotations already cover read-only/non-destructive, so the description adds real value beyond them: a hard 500-invoice cap, currency preservation, and that omission/unreviewed counts are reported (implying results may be partial). It does not explain what a 'standard' vs 'full' export mode changes or what redaction does, leaving some behavioral gaps.

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 dense sentences, front-loaded with the action and limit, no filler. The trailing clause about preserving currencies and reporting counts is slightly compressed but still earns its place.

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 should say what an export returns (a file, a signed URL, a payload?) and how the accounting formats differ, but it does not. Filters, limits, and formats are covered adequately; the return contract and mode/redaction semantics are not.

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 carries the full burden, but it only maps to a handful of the eight nested properties (format, date_from/date_to, approved_only, implicitly client_id). redact_pii, export_mode, and template_id are undocumented in both places, which is a substantial gap for an export tool where mode and redaction materially change output.

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 ('Download ... client invoices') plus scope (up to 500), filters and output formats, which is enough to distinguish it from export_saved_invoice or invoice_to_excel. However, it never names those siblings, so the 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?

'Optionally by invoice dates and approval status' hints at when the filters are relevant, but there is no explicit guidance on when to choose this over export_saved_invoice, invoice_to_excel, or create_export_template, and no stated preconditions (e.g. approval state needed, accounting file support).

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