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

Beyond the readOnly, idempotent, and non-destructive annotations, the description explains non-obvious behavior: bills don't contain transactions by default, transactions can only be enriched with account_id and include_transactions, transactions_basis may be an exact bill_id or an estimated date_window, and payments[] does not mean the current bill was paid. This is exactly the kind of behavioral context annotations cannot convey.

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 description is dense but high-signal every sentence earns its place. It front-loads the core return fields, then explains the optional transaction behavior, then covers estimates and payment caveats. There is little padding relative to the complex semantics it communicates.

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?

Even with no output schema, the description specifies the return fields, the batch response shape { results, errors }, transactions-basis semantics, estimate confidence, and cross-tool guidance. It covers the complex edge cases of pending bills, payment timing, and authoritative totals, so the tool can be invoked and interpreted correctly from the descriptions alone.

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?

With 0% schema description coverage, the description carries the burden of explaining parameters. It clearly explains bill_ids as an array discovered via a list tool, account_id as required for transaction enrichment because the bill lacks an account reference, and include_transactions as the boolean opt-in for itemized purchases. However, transactions_detail is never mentioned, leaving its enum values completely ambiguous.

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 opens with a specific verb and resource: 'Returns bill-level detail for one or more credit card bills by id', and then lists concrete fields (dueDate, billClosingDate, totalAmount, payments). It distinguishes itself from sibling tools by explicitly naming openfinance_list_transactions and openfinance_list_credit_card_bills for adjacent but different use cases.

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?

The description gives explicit routing: use openfinance_list_credit_card_bills first to discover bill IDs, use openfinance_list_transactions when transactions are needed for other purposes, and prefer openfinance_list_credit_card_bills to check paid status because this tool returns no paid/status field. An agent can choose the correct tool without additional documentation.

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