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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description is not obligated to restate safety, but it adds real value: token-only input, token expiry/invalidation behavior, and the scope limit that invoice amounts are not deleted or changed. It stops short of saying whether the restore is reversible or how the outcome is reported, which would matter for a destructive operation.

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 critical guidance (use only after preview and confirmation) is front-loaded, which is good. But 'Prepare restoring duplicate relationships between the selected invoices' restates the purpose with a wrong verb and adds noise, and 'Requires confirmation' repeats the first sentence.

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 single-parameter, destructive mutation with no output schema, the description covers the essential contract: how the token is obtained, when it expires, and what the operation does not touch. Returning-status or follow-up retrieval guidance is absent, which is the only meaningful remaining gap.

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?

Only one parameter, and schema coverage is reported at 0%, so the description must carry the semantics. It does establish that only the confirmation_token is accepted and that the token must come from this operation's preview and be current, but it adds nothing about token validation failures or error behavior. Adequate, not rich.

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 names the concrete operation (applying the change produced by preview_restore_duplicate_relationships) and the resource (duplicate relationships between invoices), so it is distinguishable from its preview sibling. However, the phrasing is muddled: 'Apply only the exact change...' is followed by 'Prepare restoring duplicate relationships', and 'Prepare' is not a real verb for a mutation tool that actually executes the change.

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 explicitly states the prerequisite (must follow preview_restore_duplicate_relationships and user confirmation of that preview) and the failure condition (changed or expired records require a new preview), which tells the agent both when to call it and when not to. The alternative path — re-run the preview — is named rather than left to inference.

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