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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real context on top: it produces a PDF with one page per customer, an aging strip, balance due, and polite reminder email drafts, and clarifies that nothing is actually sent. That negative constraint is the most important behavioral disclosure. It stops short of mentioning size limits, pagination, or failure modes for unparseable files.

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 dense sentences, front-loaded with the trigger and the input modes before the return shape and the exclusions. Every clause does work, but the statement of what the PDF contains is long and partially duplicates the output schema rather than earning new 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?

For a 12-parameter tool with nested invoice objects and an output schema, the description covers what an agent needs to decide to call it: accepted input sources, default behavior for customers and as_of_date, the two useful filters, and what it deliberately does not do. Return values need not be explained further because an output schema exists.

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 every parameter is already documented in the schema and the baseline of 3 applies. The description adds some value by enumerating the three accepted input shapes for invoices/file (typed objects, pasted CSV/TSV, attached CSV/XLSX export) and by calling out the customers and overdue_only filters, but it does not add format or edge-case detail beyond the schema.

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 names a specific verb and resource ("customer statements") and immediately pins down the domain with synonyms an agent would search for ("statement of account", "open item statement"). It also explicitly distinguishes itself from the sole sibling, generate_aging_report, so an agent can choose between them without opening either 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?

It gives an explicit trigger ("Use this when the user wants customer statements ... for customers who owe them money") and explicit exclusions ("Does not send statements or emails, and does not build an aging summary (use generate_aging_report)"). The alternative is named along with the condition that selects it, leaving nothing to inference.

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