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

Annotations declare destructiveHint=true and openWorldHint=true, establishing this is a mutating, user-visible action. The description adds meaningful context beyond these: it explicitly warns that it visibly changes what visitors see, discloses reversibility limits (the time window with the wrong live version is irrecoverable), and candidly notes frequent failure for app platforms. This transparency meaningfully exceeds what the annotation booleans convey, though without output schema or return details it doesn't reach 5.

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 compact: a purpose line, a highlighted behavioral warning, and a platform-specific proviso. Every sentence earns its place, the most critical user-impact warning is bolded and front-loaded, and no filler or redundancy exists. Excellent structure for a high-risk mutation tool.

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?

Given the output schema exists (so return format is documented elsewhere) and annotations flag destructive/open-world behavior, the description is appropriately complete. It covers purpose, safety framing, user-consent requirement, platform limitations, and failure-handling guidance. The only minor gap is not stating prerequisites (e.g., whether a prior successful deploy is required), but the schema note about 'ближайшую пригодную' partially covers this. Strong overall completeness.

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%, so both parameters (project and deploy) are documented in the schema itself. The description does not add parameter-level meaning beyond the schema; however, it implies deployment mechanics contextually. With full schema coverage, baseline 3 is appropriate — the description doesn't compensate for any gap because no gap exists.

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 description clearly states the action: return the previous working build to the live address. It distinguishes the resource (site build) and verb (rollback) precisely, and the title complements rather than tautologizes. The scope is specific and unambiguous.

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?

The description provides explicit guidance: call only when the user explicitly requested a rollback, ask first if not requested. It also names specific app types (ssr_next, streamlit, gradio, flask) where rollback often fails, and directs fallback behavior (offer rebuild, don't retry). This is model usage guidance exceeding the dimension requirements.

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