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

The description discloses that collection fields replace complete lists and that omitted fields remain unchanged, and that changes can notify clients and trigger integrations. This goes beyond the annotations, which only indicate destructiveHint. It does not explicitly warn about irreversible data loss, but the replace language is explicit enough.

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 two sentences, front-loaded with the action and target, followed by crucial behavioral notes. No redundant or irrelevant content. Efficient and clear.

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?

For a tool with 14 parameters and nested objects, the description gives key operational context: update semantics, replace behavior, and side effects. It does not cover every edge case (e.g., required order_number), but those are in the parameter schema. The description is sufficient for an agent to understand the tool's role and basic constraints.

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 already provides descriptions for each parameter (e.g., 'Replaces current tags when provided', 'Empty values delete that metadata key'). The main description adds little beyond a high-level summary of field categories. It does not introduce new parameter-specific information that isn't already in the schema.

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 updates an order's various fields (status, dates, notes, service, assignments, tags, metadata, linked orders), and distinguishes it from read-only tools. The name and action enum reinforce the write/update purpose. It is specific and 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?

The description implies when to use it (when updating an existing order) but does not explicitly contrast with alternative tools like order-read. However, the update semantics and mention of side effects (notifications/integrations) provide sufficient guidance. It could be more explicit about not using it for read-only operations, but the name and annotation cover that.

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