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

Adds real value beyond the annotations: it discloses that restoration is snapshot-based ('restoring the values the plugin snapshotted'), that it affects the live site, and that user confirmation is required before the write. Annotations already cover destructiveHint/idempotentHint, so the remaining gap is minor — it doesn't say what happens if the rollback partially fails or the snapshot is unavailable.

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?

A single sentence with the action and scope front-loaded and the safety caveat placed last as a parenthetical. No redundant restatement of the title or annotations.

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 destructive two-parameter mutation with no output schema, the description plus annotations cover the key facts an agent needs: what is reversed, on what target, and that confirmation is required. Minor omission is failure/partial-rollback behavior, which would help for destructive operations.

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 both parameters are already documented (run_id from apply_fix, project_id/slug). The description only implies run_id must reference an apply_fix run, which the schema states verbatim, so baseline 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 and resource ('Reverse the changes an apply_fix run made on the live site') and explicitly ties the tool to its sibling apply_fix, so an agent can distinguish it from apply_fix, get_fix_run, and get_fix_plan 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?

Clear usage context: this is the undo path for a prior apply_fix run, and the parenthetical 'write scope — ask the user first' gives an explicit confirmation prerequisite. It stops short of naming when *not* to use it (e.g., after the snapshot has expired or a newer run superseded it).

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