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

Annotations already declare destructiveHint=true, so the mutating nature is signaled; the description adds the useful precondition that the target must be in a cancelled state. It does not explain what the restore actually changes (number reuse, series occupancy, whether it can be undone) or any auth/rate constraints.

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?

Two short sentences, front-loaded with the action and condition. The trailing 'PUT /estimate/restore' is mild implementation trivia but costs almost nothing.

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 two-parameter mutation with no output schema, the description covers purpose and precondition adequately, but leaves out post-restore state effects and failure modes an agent would want before calling a destructive operation.

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 100% (both number and series_name are documented), so the schema carries the parameter burden and the description adds no format, syntax, or case-sensitivity detail. Baseline 3 is appropriate.

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?

States a specific verb (Restore) and resource (proforma/estimate) plus the state precondition that it must have been cancelled, which separates it from smartbill_cancel_estimate and smartbill_restore_invoice. Minor terminology drift between the tool name (estimate) and the description (proforma) leaves a small ambiguity about whether these are the same object type.

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?

No when-to-use guidance beyond the implied 'only cancelled proformas' condition. It never names the alternative sibling (smartbill_restore_invoice) to disambiguate invoice vs proforma restoration, nor states prerequisites such as required permissions or whether the original series/number must still be free.

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