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

Annotations already declare read-only, idempotent, non-destructive behavior, so the bar is lower; the description adds real context by disclosing the output shape (score, percentages, rule-of-thumb band) and cautioning that the reading is not a universal benchmark. It does not state behavior for a zero-response input (division by zero), which would be the remaining useful disclosure for a computation tool.

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?

Two sentences, front-loaded with the calculation and scope, then the usage condition. Minor internal redundancy in restating 'eNPS' and the promoter/detractor definition, but no filler.

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?

Covers inputs, formula, output range and interpretation caveat for a simple three-integer tool, and an output schema exists so return values needn't be explained. Missing only edge-case handling description (all-zero counts), which keeps it from a 5.

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 description coverage is 100% and each parameter already documents its 0-6 / 7-8 / 9-10 bucket, so the baseline is 3. The description restates those same bucket mappings rather than adding new semantics such as whether non-integer or negative counts are rejected.

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?

States a specific verb (Calculate) plus the resource (eNPS) and spells out the exact formula (percentage of promoters minus percentage of detractors) and output range (-100 to +100). This clearly distinguishes it from the payroll/date siblings, which involve no survey math.

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 'Use it when you have the count of people who answered 9-10 / 7-8 / 0-6' clause gives explicit triggering conditions, including the exact survey question context. It stops short of stating when NOT to use it (e.g., if you hold raw per-respondent scores rather than counts), so no full alternative routing.

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