undo_records

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

Annotations only say readOnly=false and destructive=false; the description adds the actual per-type side effects (corrections revert to the earlier version, theses archived, links retired, ideas withdrawn) and explicitly explains why this is non-destructive — "History keeps everything." That is real behavioral context beyond the structured fields.

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 action is front-loaded in the first clause, followed by a compact type-by-type list; no filler sentences. The phrasing "records the user doesn't want" is a slightly informal framing but costs nothing in tokens.

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?

An output schema exists, so return values need not be described, and the description covers scope, provenance, and effects. Missing for a batch mutation: whether the operation is atomic across the `records` array and how an unknown or already-undone record is handled.

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 67% and already documents record type and session provenance, but the description adds meaning the schema cannot: what each record type actually undergoes when undone. The optional `reason` parameter is left uncharacterized in both places, keeping this short of a 5.

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?

Specific verb (revert/undo) plus resource (records), and it enumerates the concrete effect per record type: claims retracted, theses archived, links retired, hypotheses withdrawn. It does not distinguish itself from sibling tools such as retract_claim or update_thesis, so an agent cannot tell from the description alone which to pick for a single claim.

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?

"Records the user doesn't want" implies the trigger condition, and "theses the session created" hints at a scope limit, but there is no explicit when-to-use/when-not guidance and no mention of the overlapping siblings (retract_claim, supersede_claim). Usage must be inferred.

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