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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description goes well beyond them: it explains the accounting rule that transfers between own accounts and credit card payments are excluded from spending, the exact deliverables (Excel workbook, one-page PDF, recurring charges with next expected date and annual cost), and the correction loop via category_overrides. Those are behavioral facts an agent cannot recover from the annotations or schema.

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?

The paragraph is dense but front-loaded: trigger conditions first, then outputs, then accounting rules, then limits. Every sentence carries information and none is a restatement of the name. It is one unbroken block, however, and the module deliverable listing could be tightened without loss.

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 six-parameter tool with nested file objects and an output schema, the description covers inputs' intent, the counting rules that shape results, the deliverable artifacts, and the correction path. An agent could call this correctly and explain the output without opening anything else.

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%, so the baseline is 3; the description earns above that by adding workflow semantics the schema does not convey — that category_overrides is applied by re-submitting the same file, and that overrides are keyed by the merchant names shown in the result (including Uncategorized). It still leaves date_order, flip_signs, account_type, and statement_year entirely to 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 gives a specific verb and resource plus concrete trigger scenarios (budgeting, subscription detection, spending by category/month) and states clearly that it produces a report rather than just categorizing. It implies its own re-invocation for corrections, which distinguishes it functionally from categorize_spending, but it never names that sibling, so an agent still has to infer which of the two to pick.

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 opens with an explicit when-to-use condition (user attaches a bank/credit card statement and asks for budget, category totals, or recurring charges) and closes with explicit exclusions (no bank connection, no scanned images without OCR, no financial advice). What is missing is only the routing to the sibling categorize_spending — the description never says when that alternative is preferable over passing category_overrides here.

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