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

Annotations already flag destructiveHint=true and non-readonly, but the description adds critical context beyond them: the exact directory scoped for deletion, the exemption of projects and uploaded media, and the mandatory user confirmation. It also implies irreversibility via 'cannot be undone' in the paired schema.

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?

Three short sentences, front-loaded with the destructive action and scope, followed by the gating condition and the required parameter. No filler.

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?

An output schema exists, so return values need not be explained. For a single-parameter destructive tool, the description covers scope, exclusions, prerequisites, and confirmation — everything an agent needs to decide and invoke correctly.

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?

Only one parameter and schema description coverage is 100%, so the baseline is 3. The description's 'Pass {confirm:true}' merely restates the schema const, adding no syntax or format meaning beyond what the structured field already provides.

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 precise verb+resource with scope: 'Delete EVERY file in the user's workspace (/home/agent) and restart it.' It also carves out what is NOT touched (projects, uploaded media), so an agent can distinguish this destructive reset from workspace_exec and the many create_* siblings.

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?

Explicit gating: 'Only when the user asks or the workspace is unrecoverably broken, and confirm with the user first.' This gives both the trigger condition and the required pre-action step, leaving nothing to inference.

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