builder_retention

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

With no annotations, the description carries the full burden and does so comprehensively: it explains cohorting (YYYY-MM, UTC), the activeWallets[k] definition, the 12-month window, the ORDERS plane vs fills, and points to dataNotes for the attribution caveat. It also states the Pro tier requirement. This is rich, non-obvious behavior disclosure.

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 somewhat long but every sentence carries essential information—methodology, definitions, contrasts, use case, and access requirement. It is front-loaded with purpose and then logically details the behavior. No fluff, so it earns a high score despite length.

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 complex retention tool with no output schema, it explains the response shape (activeWallets[k], cohorts, time coverage) and points to dataNotes for caveats. It also covers the measurement plane, prerequisites, and the intended use case, making it sufficient for correct invocation without guesswork.

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 coverage is 100%, giving baseline 3, but the description adds meaning beyond the schema: it clarifies the builder address is the fee-receiving address and notes that only the builder is needed for the core logic (the useToonFormat is format only). It also explains the builder's role in the context of first builder-fee orders, which helps the agent use the parameter correctly.

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 it is a 'Monthly retention matrix for a builder's users' with a specific verb and resource. It differentiates from siblings by naming builder_cohorts/builder_overlap and explaining the ORDERS-plane measurement difference, so an agent can distinguish it without ambiguity.

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 explicitly provides a use case: 'Use for "does builder X retain users month over month, or churn them?"' and contrasts with the attributed-fill counts on builder_cohorts/builder_overlap, giving clear when-to-use-and-when-not guidance. The Pro-tier requirement is also stated.

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