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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint = false-safe GET, and the description adds substantial behavioral context beyond them: the three transactions_basis states, 'totalAmount is authoritative — do NOT roll back to summing transactions', the payments[] caveat (payments reflect the PREVIOUS bill cycle, not a paid flag from this bill), the cost of the transactions opt-in (extra full transaction scan), and the Pluggy no-paid-field note. These are exactly the traps that cause invocers to misinterpret results. No contradiction 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?

The first sentence states the core purpose and return shape, and every subsequent sentence targets a real decision or irritate (discovery step, estimate-state, correctness warning, paid-status myth). None of the ~180 words are filler; each maps to something that would otherwise cause a wrong call or a misinterpreted result.

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?

With no output schema present, the description carries the return-format burden and it covers payments/transactions arrays and the batch shape plus batch semantics. It names the exact endpoint, repeatable idempotent semantics, the relevant siblings, and the paid caveates. The only genuine gap is the under-documented transactions_detail enum and edge behaviors (e.g., error when an id not found) — but given the batch shape, these are deemable minor.

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 carries the full burden. It explains bill_ids (array, why it's required), account_id('bill itself carries no account reference'), and include_transactions (opt-in semantics, basis behavior, cost). However, transactions_detail (enum compact/rich/raw) is never mentioned in the description or schema, leaving an agent without any basis to pick an enum value. 3 out of 4 params are richly documented; one is fully opaque, hence 4.

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+resource scope: 'Returns bill-level detail for one or more credit card bills by id (GET /bills/:id)', immediately distinguishing it from the sibling that lists bills (openfinance_list_credit_card_bills) and the one that lists account transactions (openfinance_list_transactions). It enumerates concrete returned fields, so an agent can tell exactly what this tool produces.

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?

Provides explicit sequencing ('use openfinance_list_credit_card_bills first to discover ids'), an explicit alternative for fetching transactions (openfinance_list_transactions with from/to range ending at billClosingDate), and an explicit routing preference ('To check paid status, prefer openfinance_list_credit_card_bills'). It also states when the opt-in transactions mode is unavailable (open or untagged bills use date_window).

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