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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: a default 90-day window, a hard 366-day ceiling, that drafts are skipped, and that at most 500 documents are counted. These are exactly the silent constraints that would otherwise cause a wrong call.

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 sentences, front-loaded with the trigger phrase and followed by the return payload and the scoping limit. No filler, and the exclusion is placed last as a natural boundary.

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 an output schema present, return-value detail is optional, yet the description briefly signals the shape (counts, totals, status breakdown, collection rate). Combined with the default window, caps, draft exclusion, and scope boundary, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3 and the schema already documents businessId, startDate, and endDate formats and defaults. The description nonetheless reinforces the window semantics (default 90 days, cap 366) and adds a non-parameter constraint (500-document counting cap), slightly exceeding the baseline.

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 ('how much they invoiced or were paid in a period') and enumerates the returned artifacts: invoice and payment counts and totals in business currency, invoices by status, and a collection rate. The closing exclusion ('Not for a single invoice or customer') further sharpens its scope against narrower siblings.

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 an explicit trigger ('Use this when someone asks how much they invoiced or were paid in a period, like last month') and an explicit when-not ('Not for a single invoice or customer'). It stops short of naming which sibling to use instead for per-customer or receivables questions, so routing between get_receivables_summary and this tool is left to inference.

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