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

The description goes beyond the annotations by clarifying that this tool only previews and does not apply changes itself; the actual mutation is deferred to commit_customer_import. It also discloses internal behavior (matching existing accounts by phone/email, showing deltas) and implies a server-side session is created via the returned sessionId, which is important side-effect information. This fully compensates for the lack of a readOnlyHint.

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 compact (two sentences) and front-loaded with the tool's purpose. Every sentence adds value: the first states the action and scope, the second explains the matching logic and points the user to the commit step. No wasted words.

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 the essential workflow (preview, then commit using the returned sessionId), the size limit, the matching logic, and the type of output (create/update actions and deltas). Since an output schema exists, it need not enumerate return fields, and the description does not overreach. It could mention prerequisites or required input fields, but the schema handles those, making this sufficiently complete for the tool's complexity.

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 description adds minimal parameter context beyond the schema. It mentions the 2000-row limit, which duplicates the schema's maxItems, but does not explain how to structure the 'rows' array or the purpose of 'filename'. With 50% schema description coverage, the description does not compensate for the undocumented portions of the input.

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 uses a specific verb ('Preview') and resource ('bulk customer import'), clearly distinguishing it from the sibling 'commit_customer_import' by stating the commit tool applies the changes. It also adds a concrete size limit (max 2000 rows) and describes the core function (matching by phone/email, showing create vs update actions).

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 directs the agent to use 'commit_customer_import with the returned sessionId to apply', which is clear guidance for the follow-up action. It also explains what the preview shows, helping the agent decide if this tool is appropriate. However, it does not state explicit exclusions or alternative tools for similar tasks, so it is one step below a fully explicit guideline.

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