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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known; the description adds real context on top: permission requirements (confirmation, edit, workspace invoice-view), token single-use/expiry semantics, and the fact that only an exact previewed change can be applied. That goes meaningfully beyond what structured fields provide.

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 operative constraints (preview first, user confirmation, token-only input, expiry) are front-loaded in the first two sentences. The trailing 'Prepare restoring an exact invoice from restorable trash' is redundant and slightly garbled, the one line that does not earn its place.

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 destructive, single-parameter mutation with no output schema, the description covers the confirmation flow, permission prerequisites, and token invalidation. It is silent on what happens if the invoice is no longer in the trash or what the call returns, but the key preconditions an agent needs are present.

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 reported as 0%, so the description must carry the load, and it explains that only a confirmation_token is accepted and where that token must come from (a confirmed preview). It does not repeat the min/max length constraints, but the schema's inline token description covers that; the additional meaning here is token provenance and validity.

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 first sentence names a precise verb and resource (apply the change returned by preview_restore_invoice) and explicitly ties this tool to its sibling, so an agent can distinguish the execute step from the preview step. The later phrase 'Prepare restoring an exact invoice from restorable trash' is vague and slightly at odds with the 'apply the exact change' framing, which keeps this from a 5.

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 states the prerequisite (a prior preview_restore_invoice call), the gate (user must confirm that preview), the only accepted input (that preview's confirmation_token), and the failure path (changed or expired records require a new preview). An agent has no inference left to make about when this tool may be called.

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