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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered structurally; the description still adds real value by specifying the error contract (never raises a protocol error, returns {"error": ...} with a fix hint) and that retrying after correction is safe. It slightly restates the annotations ('read-only and idempotent'), which is redundant but harmless; a 4 rather than 5.

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?

Front-loaded with the core purpose, then cost breakdown, then a concrete example, then usage boundaries, then the error/retry contract — a logical ordering with no filler. The 'FREE.' fragment is mild marketing noise but costs a single token.

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?

Seven parameters with two required, and the description covers what the tool computes, how inputs combine, the typical failure mode (ad_cost_per_order left at 0), the error shape, and the alternatives. An output schema exists, so the example return is redundant but not harmful; everything needed to invoke correctly is present.

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 the baseline is 3; the description goes beyond it with a worked input/output pair that shows units, typical magnitudes, and how payment fees and ad spend fold into total_cost, plus which output field reveals the dominant cost. It does not explain defaults or the payment_fee_pct/fixed split, so it is a modest lift over baseline rather than a full one.

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 and resource ('show what one sale actually leaves after every cost') and enumerates exactly which cost components are subtracted, plus the break-even output. It names the two closest siblings (price_ladder, returns_impact) and makes the boundary between them explicit, so an agent can pick it without opening a schema.

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?

Gives positive guidance ('use before listing a product') and two explicit exclusions with named alternatives: whole tiered price lists go to price_ladder, returns effects go to returns_impact. This is the full when/when-not/alternative pattern.

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