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

Annotations already declare readOnlyHint/idempotent/non-destructive, and the description adds real value on top: existing invoices/files remain untouched, a five-minute token is returned, and the change is explicitly not applied. The token TTL and side-effect profile are exactly the kind of operational detail annotations cannot express.

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, no filler, with the non-mutation guarantee front-loaded. Every sentence adds distinct information (replace semantics, data preservation, confirmation/token return).

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?

With no output schema, the description correctly explains what is returned (an exact preview plus a five-minute token) and what is not done. Remaining gap is the parameter-level detail for the nested input object, but the core behavior for a preview tool is well covered.

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, and it only partly does. It mentions 'name and ordered columns' and 'exact template', implying name/columns/template_id, but never explains template_id, nor the header vs source_field distinction inside each column. Partial compensation for a real coverage gap.

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 opens with a specific verb and resource: 'Prepare replacing an exact template's name and ordered columns', and makes clear it is a preview rather than the mutation. It is distinguishable from update_export_template and preview_create_export_template, though it never names those siblings explicitly. The word 'prepare' plus the title make the preview intent 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?

It implies the preview-then-confirm workflow ('Requires confirmation', 'five-minute confirmation token') and that it does not apply the change, which is useful context for sequencing. However, it never explicitly tells the agent to call update_export_template afterward with the token, nor contrasts with adjacent tools. Usage is inferable but not spelled out.

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