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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds substantial non-obvious behavior: it returns `blocked` on conflict, guarantees hand edits are never overwritten, notes session scoping, ordering, and that restored paths can shift. This is exactly the kind of context an undo tool needs beyond 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?

Three front-loaded sentences with no filler: scope and ordering first, then the exclusion, then the refusal semantics and follow-up. Every clause carries operational information (what it reverts, what it won't, when it blocks, what to do next).

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?

Despite no output schema, the description discloses the notable return signal (`blocked`), the mutation scope, conflict behavior, and the post-call read_page step. For a single-optional-parameter tool with full schema coverage, nothing an agent needs to invoke it correctly is missing.

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%, and the single `steps` parameter is fully documented in the schema (min 1, max 20, default 1). The description's 'tool call(s)' implies multiplicity but adds no syntax or limit detail beyond what the schema already provides, so the baseline of 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 ('Revert') on a specific resource (your own last editing tool call(s)), scoped to the current session and ordered newest-first. It explicitly contrasts itself with the sibling redo and enumerates the covered tool families (add/edit/delete/move/duplicate_section, insert_block, update_settings, page tools), so an agent can distinguish it without opening schemas.

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 explicit when-to-use context (last editing call this session), explicit exclusions ('Does NOT undo symbol or asset tools'), and a follow-up instruction ('call read_page afterwards') because paths may shift. The refusal condition ('when a page, CSS or settings it would restore has been edited since') tells the agent exactly when it will fail.

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