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

Annotations provide only readOnlyHint: false, so the description carries the transparency burden. It discloses the types of adjustments, the purpose (affecting Smart Bidding), the scoping behavior, and the payload structure. It does not mention potential side effects, failure modes, or idempotency, but the disclosed behavior is substantial and goes well beyond the annotations.

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?

Despite being a long single sentence, every segment adds value: adjustment types, business rationale, payload format, and scoping. The information is front-loaded with the core action and then expanded efficiently. No filler or redundant phrasing.

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?

The description covers purpose, usage context, scoping, and payload details comprehensively. Given there is no output schema, return values need not be described. Minor gaps include lack of explicit validation rules or required nested fields, but overall it is well-complete for a 2-parameter tool with nested objects.

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?

The schema only describes body as 'Adjustment payload' and space_id as an override. The description adds crucial semantics by detailing the body structure with required fields (orderId, adjustmentType, conversionAction) and optional ones (value, currency, occurredAt), and explaining the two accepted payload forms. This significantly surpasses the schema's terse descriptions.

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?

The description clearly states 'Upload one or more conversion adjustments' and enumerates the specific types (RETRACTION, RESTATEMENT, ENHANCEMENT) with concrete examples. It distinguishes itself from sibling tools like upload_offline_conversion by focusing on adjustments to existing conversions rather than new conversions.

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?

The description provides strong contextual use: 'so a refunded/churned/upgraded deal stops teaching Smart Bidding the wrong lesson.' It also explains the scoping behavior with set_active_space and space_id override. However, it does not explicitly mention when not to use this tool or compare it directly with alternatives like upload_offline_conversion.

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