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

Annotations already declare readOnly/idempotent/closed-world, and the description correctly frames this as a deterministic calculation. With no output schema, it usefully enumerates the three returned values and the benchmark interpretation. It does not discuss edge behavior (e.g., low-churn sensitivity), which is only partly covered by the schema's exclusiveMinimum on churn.

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?

Formulation, outputs, benchmark, and sibling routing are all front-loaded across four tight sentences with no redundancy. The trailing guide link is short and optional rather than diluting the core.

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 four-required-parameter calculator with no output schema, the description supplies the formula, the return fields, and a result-interpretation threshold – everything needed to call it correctly and read the output.

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 adds real value by spelling out the formula that combines arpa_monthly_usd, gross_margin_pct, and monthly_churn_pct, giving the agent a mental model of how inputs interact rather than just their definitions.

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 the exact computation (monthly revenue per account x gross margin / monthly churn) versus CAC, plus the three return values. This is clearly distinguishable from siblings such as cac_payback or burn_multiple because the inputs and outputs are named explicitly.

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?

Explicitly routes the agent: 'Use cac_payback when you only need the payback period,' which names the alternative and the condition that selects it. It also supplies an interpretation benchmark (3:1) and a guide link, so an agent knows both when to call it and how to read the result.

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