Audit a proposed advertising decision

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

Adds real behavioral context beyond the annotations: it returns a numeric chain and a counter-recommendation when the proposal is contradicted, and clarifies the three verdict states. 'Read-only' duplicates readOnlyHint=true, so that portion is redundant rather than additive.

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?

Three dense sentences, front-loaded with the purpose and immediately followed by return values and the usage rule. The em-dash enumeration of proposal sources is slightly verbose but earns its place by clarifying scope.

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?

An output schema exists, so return values need not be exhaustively explained, yet the description still names the verdicts and the counter-recommendation. Combined with the pre-action usage rule, an agent has everything needed to call it correctly.

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 every parameter is already documented in the schema (sku, source, current_cpl, cpl_trend_days, proposed_action enum, competitor_active). The description adds no format, units, or edge-case guidance for any parameter, so 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 (test/audit) and resource (an advertising decision originating elsewhere), and enumerates the three possible verdicts returned. It implicitly separates itself from siblings like recommend_next_action by scoping to decisions this server did not produce.

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 an explicit trigger: 'Use before acting on any recommendation this server did not itself produce,' which also implies the exclusion (decisions the server generated). It does not name an alternative sibling tool by name, so it stops short of a 5.

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