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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the prior values are exactly what a reversal restores (linking conceptually to reverse_audit_event), and it explains the deliberate id-suppression design of list_audit_events. It stops short of describing pagination or output ordering, so not 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?

Front-loads the return semantics in the first sentence, then justifies the sequencing. The '301 ids in a history row help nobody' aside is slightly chatty but earns its place by explaining why the sibling cannot substitute, so waste is minimal.

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 no output schema, the description carries the burden of describing the return, and it does so at the right altitude: a set of records, each with per-field prior and written values. Left implicit are pagination/limit interaction and the identity/shape of the returned records, which keeps it from a 5.

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%, so audit_event_id, connection_id and limit (default 50, max 1000) are already documented in structured data. The description adds nothing about parameter syntax or format, only about the returned payload, so the baseline 3 applies.

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: it returns the records one audit event changed, with each field's prior and written value. It explicitly distinguishes itself from the sibling list_audit_events in the same sentence, so an agent can tell the two apart without opening either 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?

Gives the exact usage condition ('the second call, made when you need to know what a write actually did rather than that it happened') and names the alternative (list_audit_events) plus why it is insufficient (returns a count, not ids). Nothing is left to inference.

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