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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds critical behavior beyond annotations: the opt-in transaction scan requirement, that transactions live on the account not the bill, that there is no paid/status field returned, that payments[] typically refer to the previous bill, and that transaction matching may be a low-confidence estimate. This directly prevents the agent from drawing incorrect conclusions from the response. No contradiction with annotations exists.

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 dense, but well-structured with clear labels such as 'ITEMIZED PURCHASES (OPT-IN)', 'Always check transactions_basis', and 'NOTE'. Key information is front-loaded: the primary purpose is in the first sentence, then the most important behavioral caveats follow. Although long, every section carries practical information an agent needs to call the tool correctly.

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?

There is no output schema, yet the description covers the response shape, batch structure { results, errors }, the reconciliation field, authoritative total behavior, and status limitations. It even gives a fallback path for fetching transactions directly and a sibling to use for paid status. For a moderately complex bill-detail function, the description supplies nearly everything an agent needs without being cluttered.

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 schema description coverage at 0%, the description carries full responsibility for parameter meaning. It explains bill_ids (array, discover via list), account_id (needed for include_transactions because the bill has no account reference), and include_transactions (opts into extra transaction scan). However, the transactions_detail enumeration (compact/rich/raw) is never explained, leaving a meaningful gap for an agent choosing a detail level for this tool.

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 a specific verb and resource: 'Returns bill-level detail for one or more credit card bills by id (GET /bills/:id)'. It clearly lists the returned fields and distinguishes the tool from the sibling list tool by pointing to openfinance_list_credit_card_bills for discovery and payment status. An agent can easily tell what this tool does and how it differs from related tools.

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 usage direction: use openfinance_list_credit_card_bills first to discover IDs, prefer that sibling for paid status, pass include_transactions with account_id for itemized purchases, and avoid summing transactions since totalAmount is authoritative. It also explains when transactions_basis should be trusted as exact versus estimated, giving the agent clear decision criteria.

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