Net Revenue Retention

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

The description aligns with annotations (readOnly, idempotent, not destructive) and adds behavioral details: computation is deterministic, uses subscription movements within window_days, returns empty when no data falls in the window, and the window range is 1–365. This is transparent and covers key behavior beyond the annotations.

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 concise and dense with useful information. Every sentence serves a purpose: defining outputs, explaining the concept, noting computation details, and providing a usage recommendation. There is no repetition or filler, making it efficient for an AI agent to parse.

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 there is no output schema, the description adequately covers what the tool returns (NRR, logo retention, split, top-losing accounts) and how it works (deterministic, window-based). For a tool with one optional parameter, this provides sufficient context for an AI agent to invoke it 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 coverage is 100%, so baseline is 3. The description enhances the parameter by explaining the default value (90 days, 'i.e. the last quarter') and the valid range. This adds practical context that helps the agent understand the parameter's meaning and constraints.

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 that the tool computes Net Revenue Retention (NRR) along with logo retention, expansion/contraction/churn split, and a ranked list of top-losing accounts. It distinguishes itself from sibling analytics tools like analyze_nps and get_retention by specifying revenue-weighted metrics and a focus on highest-loss accounts.

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 provides clear guidance on when to use the tool ('Quantify revenue health') and suggests a follow-up action ('follow the top-losing accounts into get_customer_360'). However, it does not explicitly exclude scenarios where other retention tools might be more appropriate, so there is mild room for improvement.

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