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

Annotations already declare non-read-only and non-destructive, and the description adds substantial context: preview-by-default without confirm:true, the 15-minute one-shot previewToken semantics, scan refusal, and admin-only authorization. These go well beyond what structured fields provide, though the destructiveHint=false is consistent with a restoration operation.

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?

Well front-loaded with the action and outcome, and each clause carries required detail (scope of restored items, ID alternatives, refusal, permissions, preview requirement). Slightly dense but no filler sentences.

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 mutation tool with no output schema, the description covers the safety profile (preview/confirm flow), authorization, runtime constraints (scan refusal), and the fallback listing behavior. Nothing material an agent needs to invoke correctly is missing.

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%, so baseline would be 3, but the description adds value by explaining the projectId/clientId alternative and that omitting mergeId returns a list of undoable merges. The previewToken's one-time, 15-minute, exact-arguments constraint is reiterated usefully.

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 ('Undo a merge') and ties it directly to the counterpart merge_project, clarifying the resource being restored (prompts, answers, figures, etc.). An agent can readily distinguish this from merge_project and other write tools.

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?

Explicitly names the origin (merge_project / Settings → Markets), explains the no-mergeId fallback (lists undoable merges), and states refusal conditions (active scan) plus permission gating (owners/admins). Efficiently routes the agent through the confirm/preview pattern.

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