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

Annotations already declare the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds useful output semantics (what gets computed), but no interpretation guidance, assumptions, or edge-case behavior beyond that.

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 core computation. The trailing link to the 'full version' is promotional and does not help an agent invoke the tool, which slightly dilutes an otherwise tight description.

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?

An output schema exists, so return values need not be explained, and the schema covers all parameters. For a pure deterministic calculator with complete annotations, the description supplies what the agent needs; only explicit sibling routing is missing.

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%, so every parameter (spend, orders, aov, codSharePct, codRtoPct, prepaidRtoPct, shippingPerRto, currency) is already documented. The description adds no additional parameter meaning, so the baseline 3 applies.

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?

Specific verb+resource: it computes ROAS adjusted for Return-to-Origin on COD orders, and it enumerates the outputs (delivered revenue, RTO cost, adjusted ROAS, cost per delivered order). This clearly separates it from the generic roas_calculator and roas_to_mer_converter, though it never explicitly names those siblings as alternatives.

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 context is implied by 'on cash-on-delivery orders' and the '(India COD)' framing, so an agent can infer the scenario. But there is no explicit when-to-use, when-not-to-use, or routing to roas_calculator for non-COD cases.

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