List a customer's billing documents

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states 'Read-only', 'Reads every page' (pagination behavior), explains the TypeCredit indicator semantics, and notes that the returned count is the customer's full history. It also discloses that the tool returns data 'as the Live API returns them', covering the raw format. This is thorough for a list tool.

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 multi-sentence but every sentence adds value: it opens with the core purpose, then explains the TypeCredit distinction, read-only nature, filter limitation, and pagination. It is front-loaded with the primary action and does not waste words, though it could be trimmed slightly without losing critical information.

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?

Given no output schema, the description explains the return semantics (TypeCredit distinguishes kinds) and the pagination behavior ('Reads every page'), plus the full-history count. It covers the key aspects an agent needs to interpret results correctly. It does not detail error cases or exact response fields, but that is acceptable for a list tool without an output schema.

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?

The schema has 100% coverage for both parameters (customer_ref and subscription_id), so the baseline is 3. The description does not add significant meaning beyond the schema; it reiterates that they restrict to a customer or subscription but provides no additional syntax or format details. It does add context about the overall behavior, but not parameter-specific semantics.

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 clearly states the verb 'lists' and the resource 'billing documents of a ProAbono customer', and explicitly distinguishes between debit invoices and credit notes via TypeCredit. It is specific enough to differentiate from sibling tools like get_invoice and get_credit_note, which handle individual documents.

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?

It provides clear context: this tool returns both invoice types together, and notes that there is no kind filter, advising the caller to filter the list themselves if only one kind is needed. It also mentions the count reflects the full document history. However, it does not explicitly name alternative tools for single-document retrieval, leaving some inference to the agent.

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