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

This description substantially exceeds annotation coverage. It discloses a critical behavioral trap: the platform does not return a paid/status field, that payments[] may reflect the previous bill rather than the current one, that transactions are absent from the bill payload and live on the account, that totalAmount is authoritative and must not be rebuilt from transactions, and that transaction matching can be approximate via an ESTIMATE basis. These are exactly the hidden behaviors an agent needs to avoid misuse. The annotations readOnlyHint, idempotentHint, and destructiveHint align with the read-only GET behavior and are not contradicted.

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?

Although long, every sentence in the description earns its place: the first sentence states the core return object, then each block adds necessary nuance regarding the opt-in transactions, the transactions_basis semantics, the authoritative total, the payments[] caveat, and the recommended sibling tool for paid status. The structure is coherent, front-loads the primary purpose, and then organizes edge cases and warnings. This is dense but it is dense information, not filler.

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 tool of this complexity—nested transaction matching, a mixed read/optional data-enrichment behavior, batch shape, and an important domain-specific caveat about Brazilian open-finance billing cycles—the description is highly complete. It covers the output fields, the optional transaction enrichment, matching strategies, the authoritative total, fallback fetching via a sibling, batch error shape, and status limitations. Given there is no output schema, this description is effectively the full agent-usable contract, and it is close to fully sufficient.

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 must carry the parameter semantics itself. It clearly explains bill_ids, account_id, and include_transactions, including why account_id is required when include_transactions=true. However, it does not explain the transactions_detail parameter or the meaning/impact of compact/rich/raw, leaving that one parameter's semantics entirely to the schema enum names. Because the vast majority of parameters score covered and the main trade-off is explained, the score is a strong 4 rather than 5.

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 statement: returns bill-level detail for one or more credit card bills by id, backed by the explicit GET /bills/:id route. It clearly differentiates from sibling openfinance_list_credit_card_bills by stating IDs come from that listing tool, and from openfinance_fetche non-transactions list. There is no ambiguity about what the tool returns.

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 conditions are explicit: first discover ids via openfinance_list_credit_card_bills, pass bill_ids as an array, opt into transactions only when needed because it costs an extra full account scan, and prefer openfinance_list_credit_card_bills for paid status. It also tells the agent when not to use the transactions feature and how to fetch transaction data separately via openfinance_list_transactions.

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