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

Annotations already disclose destructiveHint=true, openWorldHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds only the ambiguous claims 'MCP-confirmed' and 'commerce data stays current,' without explaining what confirmation means, whether the rollback is reversible, what permissions are required, or what side effects occur.

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?

The description is short but under-specified rather than concise: two fragments joined by a semicolon, with the second claim ('commerce data stays current') unclear in context. Brevity does not compensate for missing operative detail.

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?

This is a destructive mutation requiring four identifiers, with no output schema and no parameter documentation. The description does not explain the rollback target, the effect of release_id versus build_id, idempotency semantics, or what happens to the current published state, leaving the agent without enough context to invoke it safely.

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?

All four required parameters (workspace, build_id, release_id, idempotency_key) have 0% schema description coverage, and the description mentions none of them. Critical details such as idempotency behavior and how build_id and release_id select the rollback target are completely absent.

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?

The phrase 'MCP-confirmed source rollback' gestures at a rollback operation but uses unexplained jargon and never states what is being rolled back (a build, release, or published source) or how this differs from siblings like publish_cancel and publish_start. The title says 'Republish previous source,' but the description itself does not deliver that clarity.

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?

There is no guidance on when to use this tool, when not to use it, or which sibling tools are alternatives. 'Commerce data stays current' is not a usage condition and does not help an agent decide between publish_revert, publish_cancel, and publish_start.

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