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

The annotation `readOnlyHint: false` indicates this tool is not read-only, but the description says 'Preview' which inherently implies no modifications are made. This is a direct contradiction, requiring a score of 1 per the rules.

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 extremely concise with two sentences. The first sentence captures the core purpose and constraint. The second sentence explains the outcome and next step. No unnecessary detail.

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 presence of an output schema (not shown here but available to the agent), the description sufficiently covers the tool's behavior: it previews import, shows create/update actions, deltas, and returns a sessionId. The max rows constraint is stated. No missing information for effective 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?

Schema description coverage is 50%, and many parameters lack descriptions in the schema. The tool description adds context about matching by phone/email and output deltas, but does not elaborate on individual parameter meanings beyond what the schema provides. It provides moderate added value.

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 it previews a bulk customer import, specifies the maximum row count (2000), explains matching logic (by phone/email), and describes the output (create vs update actions plus deltas). It distinguishes itself from the sibling `commit_customer_import` which applies the import.

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 explicitly tells the agent to use `commit_customer_import` with the returned sessionId to apply the import, providing a sequential use case. However, it does not explicitly mention when NOT to use this tool (e.g., if the agent wants to commit directly without preview).

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