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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds real value beyond that: it returns an exact preview plus a five-minute confirmation token, it does not apply the change, and confirmation is required before the first saved-line edit. The only gap is what the token is used for downstream.

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 dense sentences with the purpose front-loaded and the preview/non-mutating guarantee stated last. Minor waste in 'Read tools never initialize records', which is somewhat redundant with the readOnlyHint and phrased ambiguously, but overall tight.

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 one-parameter preview tool with no output schema, the description covers what is produced (exact preview, five-minute token) and the confirmation constraint. What remains unclear is how the token is consumed in the subsequent edit call, which an agent would need to chain the workflow.

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?

There is a single parameter, input.invoice_id, with 0% schema description coverage, and the description says nothing about it. The parameter is largely self-explanatory from its name and uuid format, so the omission is minor, but the description adds no meaning beyond the schema.

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 states a specific verb+resource: it prepares/initializes saved review metadata and durable editable line IDs from printed source values, and it is explicitly a preview that does not apply the change. An agent can distinguish it from the write tool initialize_invoice_review via 'does not apply the change'. However, it never names the sibling it pairs with, leaving the pairing implicit.

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?

Usage is implied rather than stated: 'Requires confirmation before the first saved-line edit' and the five-minute token hint that this is a prerequisite step, and 'Read tools never initialize records' nudges toward a write path. But the description never says explicitly when to call this versus initialize_invoice_review or versus the other preview_* line-item tools, so the agent must infer the workflow ordering.

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