sb_undo

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description adds substantial context beyond them: conflict behavior (a page is refused if someone else saved it since), process-lifetime and capping (in-process only, capped, vs platform history surviving a restart), and redo lineage (the newest entry after an undo is its redo). The vague 'capped' without a number is the only soft spot.

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-loaded with the core purpose, then layers redo semantics, conflict handling, and scope. Sentences are dense but each carries distinct information; nothing is pure padding, though the parenthetical sibling list and trailing history note add length.

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?

For a stateful undo tool with no output schema, the description covers the critical behaviors an agent needs: what it reverts, redo lineage, conflict refusal, and process-scoped lifetime. The unaddressed dry_run parameter is the main completeness gap.

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 50%: index is documented in the schema ('1 is the most recent write'), but dry_run is undocumented in both schema and description. The description's 'No argument lists what is undoable' touches index semantics indirectly but does not compensate for the missing dry_run explanation, leaving half the parameters opaque.

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 concrete verb (put back/undo) and resource (a write's replaced content), and explicitly scopes it to edits made via named siblings (sb_add, sb_set, sb_duplicate) or a PUT through sb_api_call. An agent can distinguish this from those write tools and from the read-oriented platform history endpoint without opening any 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 clear context for use (reverting a write made here or via sb_api_call) and names an alternative for durability (the platform's own page history survives restarts). It also flags that no argument enumerates undoable items, implying a trial-by-index workflow, but does not state explicit when-not-to-use cases.

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