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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds the analytical scope (derived metrics from margin and total sales) but does not disclose output form (percent vs ratio), rounding, or behavior when optional inputs like total_sales or gross_margin_pct are omitted — relevant for a calculator with 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?

A single front-loaded sentence with no filler; every clause names a concrete output. It is efficient, though the density means nothing is expanded where clarity would help.

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 five-parameter calculator with no output schema, the description should at least indicate the shape of the result (e.g., each metric returned as a percentage) and how missing optional inputs affect output. It lists metrics but leaves the return contract and input-dependency behavior implicit.

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 60%, with the optional fields (total_sales for TACoS, gross_margin_pct before ad costs, currency default INR) already documented in the schema itself. The description only reinforces which inputs drive which metrics and adds no unit, format, or validation detail beyond that — 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?

States a specific verb (Calculates) and a precise set of resources (ACoS, ROAS, break-even ACoS, profit after ads, TACoS), so an agent knows exactly what comes out. It never distinguishes itself from siblings like roas_check or break_even, which overlap on ROAS and break-even logic, so an agent cannot confidently choose between them from this text alone.

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?

No when-to-use or when-not-to-use guidance is present, and no alternatives are named despite roas_check and break_even covering adjacent ground. The agent must infer that this is the right tool whenever Amazon ACoS comes up.

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