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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds crucial behavioral context: the transactions_basis semantics (bill_id vs date_window vs unavailable), the authoritative nature of totalAmount (do NOT rebuild), the fact that payments[] reflect previous bill cycles, and the note that Pluggy doesn't return a status field. No contradictions with 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?

Despite being long, every sentence adds critical information: purpose, opt-in mechanics, basis meanings, payment caveats, and alternative routes. It is well-structured with backticked parameters and clear warnings, front-loaded with the core function and then layering details. No wasted words.

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 complex tool with intricate matching logic and financial caveats, the description covers everything an agent needs: response shape, the transactions basis enum, the authoritative total, payment semantics, batch response shape, and how to obtain transactions if not included. Without an output schema, it fully describes the return values. Nothing missing for correct invocation.

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 has 0% description coverage, so the description carries full burden. It thoroughly explains bill_ids (array, discover via list tool), account_id (required for include_transactions), and include_transactions (opt-in, cost). However, transactions_detail (a parameter with enum compact/rich/raw) is not mentioned at all. This leaves a gap for that parameter, so it is not complete.

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 exactly what the tool does: returns bill-level detail for one or more credit card bills by ID. It names the specific fields returned and clearly differentiates from siblings like openfinance_list_credit_card_bills (which is for discovering IDs) and openfinance_list_transactions (which fetches raw transactions). The verb 'Returns' plus the resource and the method path make the purpose unambiguous.

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?

Gives explicit when-to-use: instructs to call openfinance_list_credit_card_bills first to discover IDs. It also provides an alternative path for fetching transactions via openfinance_list_transactions with a from/to range ending at billClosingDate. It warns about the cost of the opt-in transaction scan and the misinterpretation of payments[] regarding paid status. All this gives an agent clear decision rules.

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