Insert or update a promotion

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

Annotations already mark readOnlyHint=false, but the description adds valuable context: the data source body quirk, required fields, and async approval with promotionStatus returned. This goes beyond annotations by explaining the write behavior and return value. It doesn't cover potential side effects of updates or error cases, but the disclosed behavior is substantial.

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?

The description is four sentences, front-loaded with the core action and then key caveats. Each sentence adds non-redundant information, though it's slightly long for a simple tool. The logical flow from action to quirk to requirements to return/async works well.

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?

Given the nested promotion object and no output schema, the description covers requirements, optional attributes, return type, and async workflow. It also points to get_promotion for later status checks, making the tool's place in a workflow clear. No major gaps are apparent.

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 already covers all three parameters, but the description adds extra meaning: it clarifies the data source travels in the body despite being a parameter, lists required fields within the promotion object, and decodes optional attributes like couponValueType and promotionEffectiveTimePeriod. It also adds ISO/CLDR format details not in the schema, significantly enriching parameter understanding.

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 opens with 'Creates or updates a promotion,' clearly stating the action and resource. It distinguishes from sibling tools like insert_product_input and get_promotion by specifying it handles promotions and noting an upsert behavior, making its purpose unambiguous.

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?

It says 'Unlike product writes, the data source travels in the request BODY,' providing a specific usage note that differentiates this from product-oriented tools. It also directs checking get_promotion later for async approval, offering a follow-up path. However, it doesn't explicitly state when not to use this tool, so it misses a complete exclusion list.

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