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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: the pricing is derived from the seller's settlement data (price, Amazon fees, storage, saved unit costs) rather than catalog price, and the output contains a `narrative` field that should be treated as the answer. That output-shape hint is valuable given there is no output schema. It does not cover freshness/lag or whether SKU margin overrides account-level margin when both exist.

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 purpose, then the metric enumeration (justified since no output schema exists), then a direct instruction on how to read the response. Dense but every clause carries information; the parenthetical cost list is the only mildly compressible part.

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 read-only, all-optional-parameter tool with no output schema, the description does the needed work: it names the computed metrics, discloses the settlement-based cost model, and points at the `narrative` field as the primary answer. Remaining gaps (data lag, units/currency of the figures, what happens with no settlement data) are secondary rather than blocking.

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% and the schema descriptions are already rich (sku scopes to that SKU's own margin, days is 1-90 with default 30, marketplace_id is inferred when single). The description adds no syntax or interaction detail beyond the schema, 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?

States a specific verb/resource: net contribution per ad group, with the metric set it computes (spend, ad sales, ACoS, CPC, affordable CPC ceiling, kill candidates). The ad-group grain plus the 'priced with the seller's own economics' framing distinguishes it from get_profit_by_sku and get_profit_summary, though it doesn't explicitly name those siblings.

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 is only implied: the mention of 'kill candidates' and 'the highest CPC each ad group can afford' suggests this is the tool for pruning or bidding on ad groups, and 'read its narrative as the answer' tells the agent how to consume the result. There is no explicit when-to-use / when-not / alternative-sibling guidance despite many adjacent profit and ads tools.

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