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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds the computation formula and an interpretation rule ('Above 100% NRR means existing customers grow on their own'), but it never explains how GRR is derived (implicitly NRR without expansion) or what the response contains, despite no output schema.

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 definition and formula are front-loaded, the interpretation sentence earns its place, and the exclusion rule is appended efficiently. The external guide URL is marginal but not disruptive.

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 simple four-parameter calculator with no output schema, the description covers definition, formula, and interpretation. It leaves two meaningful gaps: whether GRR is returned alongside NRR and how GRR is defined, which an agent calling a tool titled 'Net and gross revenue retention' would reasonably expect.

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 the schema already documents all four parameters with defaults and minimums. The formula in the description maps each input to a term (expansion, contraction, churn, starting revenue), which reinforces the semantics but adds little beyond the per-parameter descriptions. Baseline 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 states the specific metric computed (NRR and GRR) for a defined cohort over a period and gives the exact formula, so an agent knows this is a retention-metric calculator. It is clearly distinguishable from siblings like burn_multiple or rule_of_40 by naming the resource and the calculation. It stops just short of an explicit 'computes/returns' verb.

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?

'Exclude revenue from new customers' is a genuine input constraint, and 'usually 12 months' gives period guidance for the cohort. However, it never names alternatives or states when to choose NRR/GRR over sibling calculators, so usage is implied rather than directed.

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