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

Annotations already signal read-only, idempotent, non-destructive. The description goes far beyond that, disclosing that transactions are not in the bill payload and require an extra scan, that transactions_basis may be an estimate, that bill totalAmount is authoritative, that payments[] refers to the previous bill's payment, and that Pluggy returns no paid/status field. This gives the agent strong behavioral grounding.

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, yet every sentence carries material decision-making weight: return shape, opt-in consequences, authoritative fields, known limitations, alternative routes, and required calls. It is front-loaded with core output and progressively adds caveats, so it remains to learn.

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 no-output-schema tool, this description provides a surprisingly complete contract: request semantics, response fields, batch shape with results and errors, edge-case behavior for open bills, estimate sources, paid-status guidance, cost considerations, and aliases. Nothing essential is missing for an agent to select and invoke this tool correctly.

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%, and the description compensates for most parameters: bill_ids as an array, account_id required for include_transactions, include_transactions as opt-in, plus caveats about their meanings. The only missing semantic coverage is transactions_detail and its enum (compact/rich/raw); the values are self-describing, but the description does not connect them to the include_transactions flow.

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 and resource: 'Returns bill-level detail for one or more credit card bills by id (GET /bills/:id)' and lists the returned fields. It clearly identifies itself as a detail-fetching tool for a known bill id and is easily distinguishable from siblings like openfinance_list_credit_card_bills.

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 gives explicit guidance: use openfinance_list_credit_card_bills first to discover ids, prefer openfinance_list_credit_card_bills for paid status, and use openfinance_list_transactions for fetching transactions separately. It also explains when the include_transactions opt-in is useful and not necessary, making the tool's place among siblings unambiguous.

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