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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds that figures are annualised and names the MRR components, but it does not discuss edge cases, calculation assumptions, or behavior beyond the structured 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 a compact single sentence followed by a reference link, front-loading the metrics and inputs. It is efficient, though the external link is ancillary and not essential to invocation.

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?

With an output schema present and 100% schema description coverage, the description only needs to frame the purpose and inputs, which it does. It omits any note about period granularity or edge conditions, but those are largely covered by the schema.

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 baseline is 3. The description goes further by explicitly mapping the starting, expansion, contraction, and churned MRR inputs to the retention calculation, adding conceptual meaning beyond the field names; only period is left to the schema.

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 specific metrics computed (NRR and GRR) and identifies the input components (starting MRR, expansion, contraction, churned MRR). It does not explicitly distinguish itself from sibling calculators such as calculate_arr or calculate_churn, so it stops short of a 5.

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?

Usage is implied by the metric definitions, but there is no explicit when-to-use guidance, no exclusions, and no reference to alternative tools like calculate_churn or calculate_arr. The link to an external calculator is supplementary rather than a usage rule.

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