swebsy_undo

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

No annotations are present, so the description carries the full behavioral burden and does so well: it discloses the refusal mechanism ('blocked') and its condition, the newest-first ordering, and the follow-up requirement (read_page) because paths may shift. This is exactly the extra context an agent needs beyond the schema.

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 dense sentences, each earning its place: scope, exclusions, refusal semantics, and the follow-up tip. Front-loaded with the action and its scope before the caveats.

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?

Complete for a single-param revert tool with no output schema; it covers scope, exclusions, failure mode, and post-call advice. The only minor gap is no mention of the maximum of 20 steps, but that is in the schema.

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% (the steps param is fully documented with default and range), so baseline 3 applies. The description implies multi-step revert via 'call(s) … newest first' but adds no format or semantic detail beyond the schema.

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 precise verb (revert) and scope (own last editing tool calls this session), and enumerates which tools are covered. The explicit exclusion of symbol/asset tools distinguishes it from siblings like delete_symbol and upload_asset.

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?

Clearly says when it applies (your own edits this session) and when it does not (symbol or asset tools), and names the sibling that handles the follow-up (read_page). It lacks explicit guidance on when to prefer this over sibling swebsy_redo.

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