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

Annotations only say readOnly/idempotent/non-destructive; the description adds the pieces annotations cannot express – an accounting-setup permission requirement, the issuance of a five-minute confirmation token, and that the preview is 'exact' rather than approximate. That is meaningful context a caller needs before invoking.

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?

Three short sentences, front-loaded with the action, then prerequisites, then return/expiry semantics. Nothing is redundant and no sentence could be dropped without losing information.

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?

No output schema exists, and the description compensates by describing the return (exact preview plus a five-minute confirmation token). The gap is input-side: for a nested name/columns/header/source_field payload with no schema descriptions, it should say where allowed source fields are enumerated.

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 0%, so the description must carry parameter meaning; it hints at a template 'name' and 'source fields' but never explains 'header', the 1-100 column limit, or where valid source fields come from. Notably it says 'supported source fields' without pointing at the sibling list_export_template_fields, leaving the most important input constraint unresolved.

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?

Specific verb+resource: 'Prepare a named CSV column template using supported source fields', followed by an explicit statement that it returns a preview and 'does not apply the change'. That last clause is what separates it from the apply-path sibling create_export_template, so an agent can tell the pair apart without opening either 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?

Gives concrete usage conditions: confirmation is required (via a five-minute token) and accounting-setup permission is needed, which tells the agent this sits in a two-step preview-then-apply flow. It does not explicitly name create_export_template as the tool to call afterwards, so the routing is implied rather than stated.

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