Net Revenue Retention

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds substantive behavioral detail: it is 'computed deterministically off subscription movements inside window_days', includes the default and valid range (90, 1–365), and the edge case of being 'empty when none fall in the window'. This goes well beyond annotation information.

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 with a distinct role: enumerate outputs, explain the key interpretative insight, and specify computation/usage. The description is front-loaded with the most important information and contains no filler or redundant phrasing.

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 tool with no output schema, the description adequately specifies what the return contains (NRR, logo retention, split, ranked losing accounts), the computation basis, and the edge case. It also provides a workflow suggestion, making it self-sufficient for an agent to select and invoke 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 for window_days is 100% with type, default, minimum, and description. The tool description adds 'valid 1–365', a maximum not present in the schema, and explains its role in the computation. This is a useful addition but the schema already carries most of the parameter meaning, so a baseline of 3 is appropriate.

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 explicitly identifies the tool's function: computing Net Revenue Retention (revenue-weighted) alongside logo retention (count-weighted), including the expansion/contraction/churn split and the top-losing accounts by MRR. It clearly distinguishes itself from sibling retention tools by focusing on the divergence between logo and revenue retention, and even points to get_customer_360 as a follow-up.

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 a clear context: 'Quantify revenue health, then follow the top-losing accounts into get_customer_360.' This gives an explicit use case and workflow. However, it does not explicitly state when not to use this tool or how it compares to alternative retention metrics like get_retention, so it lacks full exclusion guidance.

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