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

With no annotations at all, the description carries the full burden and does well: "Writes nothing" declares the safety profile explicitly, and it spells out the return contents and that next_actions will contain follow-up steps. Gaps remain around operational limits (max CSV size despite maxItems 300) and any auth constraints, which would matter for a bulk-reading tool.

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?

Four short sentences, front-loaded with the dry-run guarantee and the return shape, then the workflow instruction. Nothing is redundant and the most decision-relevant fact (writes nothing) appears first.

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 6-parameter tool with no output schema, the description covers the essentials: it explains what comes back (headers, mapping, per-row outcome/problems) instead of relying on an output schema that does not exist, and it points to next_actions. Remaining gaps are shop scoping and how the previewed mapping should be fed into imports.run.

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 only 33%, so the description needs to compensate more than it does. It does clarify that the suggested mapping derives from a preset or the header names, tying preset and mapping together, but it never mentions shop_id, the csv format expectations, or how on_match affects the previewed rows -- even though on_match carries its own schema description.

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?

"Dry run of a customer CSV import" gives a specific verb and resource, and the description immediately separates this tool from the write path by naming imports.run. The return contents (headers, suggested mapping, per-row outcomes) further pin down what the tool is, so an agent can distinguish it from imports_historyPreview or imports_paymentHistory without opening the schema.

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 gives explicit sequencing guidance -- "Show the mapping to the owner before imports.run" -- which tells the agent both the precondition and the follow-on tool. It does not explicitly exclude the other import siblings (imports_fields, imports_historyPreview, imports_historyRun), so an agent handling a non-customer import is left to infer routing from the word "customer".

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