affiliate_rakuten_list_transactions

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

With no annotations, the description carries the full burden. It discloses that the tool returns Transaction records including a derived ageDays field and supports date-window or programme filtering. However, it does not mention pagination, default limits, authentication needs, or read-only nature, leaving some behavioral traits uncovered.

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?

Three sentences, each adding unique value: purpose and scope, example queries, and return type plus a pairing guideline. No redundancy or filler; fully front-loaded.

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 9-parameter tool with no output schema and no annotations, the description covers core functionality, examples, and the derived ageDays field. However, it leaves pagination parameters, date format, and full response structure undocumented, which are gaps given the tool's complexity.

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 0% description coverage, but the description adds meaning by mapping key concepts: date windows (from/to), programme filtering (programmeId), and statuses (earned, pending, reversed, paid). It does not explain limit, cursor, offset, or min/maxAgeDays explicitly, so parameter coverage remains partial.

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 tool lists affiliate transactions on Rakuten Advertising, with specific statuses (earned, pending, reversed, paid) and filtering options (window or programme). It distinguishes from sibling tools like list_clicks and get_earnings_summary by focusing on transactions and even suggests pairing with the summary tool.

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 example queries ('what did I earn last month?', 'what's still pending?', 'show me reversed sales') and recommends pairing with get_earnings_summary for aggregate totals. It lacks an explicit 'when not to use' statement, but the provided context strongly signals appropriate usage.

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