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

Annotations only declare readOnlyHint=true, but the description goes far beyond that: money is integer cents per currency and never converted, only issued invoices count (drafts/cancelled excluded), the 150-row truncation with whole-business-day cuts and lines_cut/next_call, the optional second content block as copy-ready text, MCP Apps rendering with a Copy button, and that the tool is free. It also names the exact error codes and their triggering conditions (NOT_FOUND, VALIDATION_ERROR per field, PAYLOAD_TOO_LARGE).

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?

It is a single dense paragraph of roughly 200 words, but nearly every clause carries distinct operational information rather than restating the name. Front-loading is reasonable — the content of the statement comes first and the refusals last — though the key 'returns figures only, prepares nothing' disclaimer sits mid-paragraph where it would be more valuable up front.

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?

There is no output schema, so the description carries the full burden of describing return values, and it does: the per-currency sections, cents convention, ageing buckets tied to sales_receivables, document_path, pdf_next_call, lines_cut and the secondary text content block. Combined with explicit failure modes, an agent has everything needed to call this correctly and interpret the result.

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 100% and already documents client_id, from and to including defaults, so the baseline is 3. The description adds semantics not in the schema: dates are interpreted in the business's own sales_settings time zone, periods longer than 366 days are rejected, and a from after to or a to after today is a VALIDATION_ERROR naming the field — genuine added meaning over the parameter definitions.

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?

The description precisely enumerates what the statement contains (opening balance, invoices, payments, credits, write-offs, running balance, closing, ageing buckets) and explicitly disclaims action: 'It prepares nothing and sends nothing: returns the figures.' The only weakness is that the opening is a long noun phrase rather than a verb+resource statement, so the actual operation surfaces several clauses in. It does, however, clearly separate itself from statement_pdf and sales_receivables.

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?

It routes the agent to alternatives in several concrete cases: use invoice_client_search or invoice_client_list to obtain a valid client_id, follow up with statement_pdf (via pdf_next_call) to get the PDF, and fall back to sales_receivables when a client exceeds 2000 issued invoices. It never states a condition where a different statement-ish tool should be preferred over this one in the normal case, so it stops short of full when/when-not guidance.

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