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

Annotations already declare readOnlyHint: true, idempotentHint: true, and destructiveHint: false, so the safety profile is covered. The description adds substantial behavioral context: transactions_basis can mean exact bill_id matching or an estimated date_window, the bank payload carries no transactions, the bill's totalAmount is authoritative and not to be recomputed by summing transactions, and payments[] can refer to the previous bill, not the current one. There is no contradiction between description and annotations.

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 long but every sentence carries information: it starts with the core return shape, then explains the opt-in transaction behavior, then flags estimate vs. exact basis, and closes with a critical paid-status caveat. It uses inline alerts like 'do NOT rebuild it' and 'do NOT assume' to emphasize important nuances, and has no filler or repeated schema 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?

Given there is no output schema, the description does an excellent job of documenting both the standard response fields and the opt-in transaction enrichments, including transactions_count, transactions_sum, and reconciles_with_total. It also covers the batch shape, the fee-account dependencies, and how to derive the missing paid status from a sibling tool. An agent would know how to call this correctly and how to interpret the results.

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?

Despite the schema having no parameter descriptions, the description meaningfully explains bill_ids as an array to be discovered via list_credit_card_bills, and explains that include_transactions: true must be paired with the credit card account_id because the bill payload carries no account reference. The only parameter not clarified is transactions_detail; compact/rich/raw are not defined, which is a small gap given the otherwise high level of detail.

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 states explicitly that the tool 'Returns bill-level detail for one or more credit card bills by id' and lists specific fields, which is a clear verb+resource combination. It also distinguishes itself from siblings by explaining where transactions actually live (on the account, not the bill payload), helping an agent separate this from openfinance_list_credit_card_bills and openfinance_list_transactions.

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 provides strong usage routing: it says to use openfinance_list_credit_card_bills first to discover ids, mentions openfinance_list_transactions as the alternative for fetching transactions directly, and explicitly advises preferring openfinance_list_credit_card_bills for paid status because this endpoint has no status field. It even warns about a common misunderstanding of payments[] and when the estimate vs exact basis should be trusted.

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