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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description still adds real value beyond that: what survives the deletion (pending requests and invoice history are retained), the token expiry/re-preview rule, and the approval-scope authorization requirement. It does not say what is returned or how failures surface, which keeps it short of a 5.

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 sentences, roughly 70 words, with the gating procedure front-loaded and no filler. The opening 'Apply only the exact change...' is slightly procedural before the purpose lands, but nothing is redundant enough to cut.

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, non-idempotent-looking mutation with no output schema, it covers the preview-confirm flow, the token lifecycle, what data is preserved, and the authorization scope. The remaining gap is what a successful call returns (a job id resolved via get_result, presumably), which the description leaves implicit.

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 only one parameter, and the description adds semantics the schema doesn't fully carry: the token must be the one from this operation's preview, it is consumed once ('only'), and it expires when the underlying record changes. That is meaningful context for a single-parameter tool whose top-level schema coverage metric is 0%.

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 pairs a specific verb ('permanently deleting') with a specific resource ('an exact approval configuration rule') and explicitly names the sibling it depends on (preview_delete_approval_rule), so an agent can place it against update_approval_rule and the preview variant without opening any schema.

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 precondition (only the exact change returned by preview_delete_approval_rule, after user confirmation), the exclusion (changed or expired records require a new preview), and the additional gate ('Requires approval-scope confirmation'). When-to-use, when-not-to-use, and the alternative are all explicit.

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