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

Annotations already mark destructiveHint=true, but the description adds critical detail: what data is wiped versus retained (credentials, API keys, namespace, tenant), the validation order (bad bundle is a no-op), and the post-wipe publish step. This goes far beyond the annotation's binary flag and fully discloses the tool's behavior and side effects.

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 dense but well-organized. It front-loads the destructive warning and conditions, then explains the validation order and post-action. Every sentence adds value: the retention details, the mode restriction, the validation safety, and the build_publish reference. There is no redundancy, and the structure leads the reader from warning to conditions to workflow.

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, multi-step tool with 6 parameters, the description covers all essential aspects: purpose, prerequisites, safety confirmation, validation behavior, and the next step (build_publish). It also mentions files_ref for large bundles, addressing a common constraint. Even without an output schema, the description is sufficient for an agent to invoke the tool correctly and understand the consequences.

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 67%, and the description enriches the two key parameters: confirm_project_name (safety confirmation) and files (validated before wipe). However, app_type has no schema description and the description doesn't mention it, leaving that parameter underdocumented. For the critical parameters, the description adds significant meaning beyond the schema, but the gap for app_type prevents a perfect score.

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: 'completely replace a DEV-mode project's app' with explicit destructive semantics. It specifies the resource (project's app), the scope (DEV-mode only), and the safety condition (confirm_project_name). It distinguishes itself from sibling tools like build_update_project and build_publish by emphasizing the wipe-and-replace nature, making its purpose 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 usage conditions: 'DOMAIN-admin keys only', 'Refused if mode='live'', and the requirement for confirm_project_name. It also explains the conditional workflow: if files are passed, they are validated before wipe and published after; otherwise wipe-only then call build_publish. This gives clear guidance on when to use and what to expect, including the fallback to build_publish.

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