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

Goes well beyond the annotations: discloses the license tier, the error contract (never raises a protocol error; returns {"error": ...} with a fix hint), and that retrying after correction is safe. The worked input/output pair also shows the actual computation shape and effective_fee_pct, which the annotations do not cover.

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?

Purpose is front-loaded in the first sentence, followed by the gating note, example, usage caveat and error contract in a sensible order. The embedded JSON example is somewhat sprawling across line breaks and is the only mildly wasteful element, though it does earn most of its space.

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 5-parameter, single-required-field estimator with an output schema, the description covers everything an agent needs: purpose, license gate, error behavior, retry safety, and a sanity-check example. Return-value explanation is technically redundant given the output schema, but it does not leave gaps.

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 adds real value by showing how the parameters interact in a concrete call (order_total 84.5, fee_pct 2.9, fee_fixed 0.3, orders 120, refund_rate_pct 4) and what effective_fee_pct results. It stops short of explaining edge semantics like refund interaction with fixed fees, so it is a notch below a full 5.

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?

Opens with a specific verb and outcome: "Estimate what actually lands in the bank after processing fees." That is unmistakably a net-payout calculator, and no sibling (bulk_price_change, metafield_key_check, product_csv_check, url_handle, variant_matrix) overlaps with it, so an agent can select it without ambiguity.

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 states the intended use ("Use for cash-flow planning") and an explicit exclusion ("Not as an authoritative fee schedule: rates depend on your plan, country and card mix, so pass your own"). It also notes the PREMIUM (license) prerequisite, which is a gating condition the agent needs before calling.

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