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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description goes well beyond that: it reveals that the bank's bill payload carries no transactions (they live on the account), that proprietary math matches exact (bill_id) only for closed bills while date_window is an estimate (confidence: low) for open bills, and that payment history reflects a PREVIOUS bill cycle. These are genuine, high-value disclosures, but the text gets muddled when it references transactions_hint:false — which is not a schema parameter — and advises computing total yourself while the same paragraph says the bill's totalAmount is authoritative and should not be rebuilt.

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 core contract is front-loaded in the first sentence and the long additional guidance is split into distinct paragraphs with their own purpose: opt-in transactions, transactions_basis semantics, totalAmount warning, bill discovery, batch shape, and paid-status gotcha. The length is justified by the domain complexity, though a few garbled phrases ('use transactions_hint:false', 'If the response carries a transactions_hint') and one contradicting piece of advice keep it from scoring a 5.

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?

Given the absence of an output schema, the description carries the complete return contract: the bill fields, the optional transactions arrays, the transactions_basis semantics, the batch shape { results, errors }, and the absence of a paid/status field. It does not close every gap though — what happens when include_transactions=false is only implied, the meaning of the transactions_detail levels is unspecified, and the transactions_hint reference is confusing to honor.

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 0%, so the description must carry all the parameter meaning — and it compensates well for three of four parameters: bill_ids (array, use list bills first), include_transactions (opt-in, requires account_id because the bill has no account reference), and account_id. However, the transactions_detail enum (compact/rich/raw) is never mentioned in the description, so an agent cannot make an informed choice about the one parameter with meaningful options; this is a real gap when the schema alone provides that check.

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 plus resource: 'Returns bill-level detail for one or more credit card bills by id (GET /bills/:id)' and enumerates the returned fields (dueDate, billClosingDate, totalAmount, financeCharges, payments[]). It also clearly separates itself from siblings: openfinance_list_credit_card_bills is framed as the id-discovery step and openfinance_list_transactions as the alternative way to fetch transactions, so the tool's unique role is unmistakable.

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?

Usage routing is explicit and actionable: 'Pass bill_ids as an array — use openfinance_list_credit_card_bills first to discover ids', and 'To check paid status, prefer openfinance_list_credit_card_bills which derives payment_status via cross-bill match'. It also tells the agent when NOT to do things: do NOT rebuild totalAmount by summing transactions, and do NOT assume the bill was paid just because payments[] is non-empty, with the concrete alternative of calling openfinance_list_transactions when the opt-in is unavailable.

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