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

Beyond the readOnly/idempotent annotations, it discloses the comparison methodology (same number of days before and after), the judging criterion (profit per day, not ACoS), and that it flags periods that have not settled yet – real behavioral nuance an agent can't get elsewhere.

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 question and verdict logic, then the metric list, then defaults and usage triggers. Dense and mostly purposeful, though the single long run-on sentence packs many clauses and could be broken for scanability.

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?

With no output schema, the description carries the return burden and does so: it lists the metrics returned and points the agent at `narrative` as the answer. Combined with the default-selection rule and judgment criterion, an agent has everything needed to call and interpret it.

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 documents both params, so baseline is 3; the description earns an extra point by specifying the fallback semantics of omitting promotion_id (most recent ended promotion, else the running one), which the schema does not state.

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?

Names a specific analysis (promotion profitability via before/after equal-length windows) and enumerates exactly what it compares: units/day, avg price, conversion, contribution per unit, ad spend, profit per day. This clearly distinguishes it from get_promotions (which lists promotions) and did_my_changes_work.

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 concrete user-intent triggers ('did my deal work', 'was the Black Friday discount worth it') and states the default selection rule when promotion_id is omitted. It implicitly points at get_promotions for IDs but never explicitly excludes or contrasts with it as an alternative.

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