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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write-but-non-destructive profile is covered. The description adds genuinely useful context the annotations lack: the $0.10 cost, the API-key requirement, and the retry-safety semantics of request_id. It stops short of 5 because it never says what state is restored or what happens to the original correction record.

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 compact clauses, front-loaded with the action and resource, then the retry rule, then cost/auth. No filler, and every element is actionable.

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?

With an output schema present, return values need not be described, and the annotations cover the safety profile. The description rounds this out with cost, auth, and idempotency. It is slightly incomplete in not clarifying the correction_id vs 'ledger ID' terminology or any permission requirements.

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 coverage is only 33%, so the description must compensate. It explains request_id's role (retry safety), but it refers to the identifier as 'ledger ID' while the schema names the required field correction_id, an inconsistency that adds ambiguity rather than clarity. The idempotency_key alias is documented only in 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?

States a specific verb+resource (undo an event fact correction) plus a scoping qualifier ('owned') and the lookup key ('by ledger ID'). It is clearly the inverse of the sibling apply_event_fact_correction, though it never names that sibling explicitly, so it stops short of full sibling differentiation.

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?

The line 'Supply request_id for safe retries' gives one concrete usage rule (idempotent retry), but there is no guidance on when to undo versus re-apply, restore, or use list_event_fact_corrections first. Usage is implied rather than framed.

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