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

Goes well beyond the annotations: it discloses exactly what state gets restored, that a report revert creates a NEW head version with history kept, the taxonomy of refusals (change_not_found including the 30-day and ownership limits, already_undone, changed_since with all-or-nothing batch semantics), an access tier requirement, and the fact that the reply carries a fresh `undo`. That is precisely the mutation and failure surface an agent needs, and it is consistent with destructiveHint=false and idempotentHint=false.

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 effect, then the parameter source, then restore semantics, refusals, chaining, and access tier — a logical order with little filler. It is dense as a single block, but every clause (including the named error codes) conveys actionable information for the calling agent.

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 no prose. Given a one-parameter mutation, the description covers effect, prerequisites, failure modes, reversibility of the undo itself, and plan-gating — nothing material is missing for correct invocation.

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 100% for the single parameter, so the schema already defines `change_id`. The description still adds value by enumerating which tools emit a usable `change_id`, turning an opaque string into a traceable token and implicitly ruling out self-invented values.

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 and resource ('put a record back as it was before one write') and scopes it to a single reversible write, which separates it from sibling mutators like restore_deleted or update_signal. The agent knows exactly what the tool accomplishes without reading the 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?

Explicitly tells the agent where the `change_id` comes from (the `undo` field of update_signal, update_report, mark_inbox_read, stage_action) and states the conditional limit that a staged action can only be withdrawn while still pending. It stops short of contrasting against alternatives such as restore_deleted or approving/rejecting a staged action, so usage is clear but not fully disambiguated.

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