Доставка: свойства посылки [sandbox]

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

The description does not contradict annotations (readOnlyHint=false is consistent with 'change'). However, it adds no behavioral context beyond annotations: no mention of side effects, required permissions, or whether changes are reversible. With annotations present, the description should provide additional context but fails to do so.

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 a single short sentence, making it front-loaded and concise. However, it is too brief given the tool's complexity (4 parameters, nested objects). It sacrifices completeness for brevity, which is acceptable only if other sections provide details, but they do not. Efficiency is lost due to under-specification.

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 fails to provide sufficient context for an agent to use the tool correctly. It omits how properties are structured, what values are allowed, the effect of changes on existing orders, and any constraints. With no output schema and vague parameter descriptions, the tool is incomplete for safe autonomous use.

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?

Although schema coverage is 100%, the descriptions for the two required parameters (orderId, properties) merely reference external swagger files, which are inaccessible to the agent. The optional parameters (dryRun, idempotencyKey) are well-described, but the tool description does not compensate for the inadequate schema descriptions. The agent lacks understanding of what 'properties' means.

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 that the tool changes delivery parameters (properties) of the parcel. This provides a specific verb ('change') and resource ('delivery parameters/properties'). However, it does not differentiate from siblings like delivery_set_order_real_address or delivery_change_parcels, which overlap in scope. A more explicit description of what constitutes 'properties' would improve clarity.

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?

There is no guidance on when to use this tool versus alternatives (e.g., delivery_change_parcels, delivery_set_order_real_address). No prerequisites, context, or exclusions are provided. The agent must infer usage from the name and vague description, which is risky given the many sibling delivery tools.

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