Erase the workspace (owner only); confirm must equal the workspace id

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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description carries the load and does so: it discloses destructive intent, the owner permission requirement, and that there is no server-side dry run. It still says nothing about cascade effects, recoverability, or what a successful deletion leaves behind.

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?

Two compact sentences with the destructive action and the permission constraint front-loaded, and no filler. The compressed 'confirm' phrasing is where clarity is sacrificed for brevity.

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 high-stakes destructive tool with no output schema, it covers the essentials an agent needs before calling: what is destroyed, who may do it, that execution is gated client-side, and that no server-side rollback preview exists. Big-picture operational detail (recovery, cascades) is missing but is arguably outside a tool definition's scope.

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%, so the schema already documents the top-level confirm boolean and idempotencyKey. The description adds that confirm 'must equal the workspace id,' which suggests the nested body.confirm string rather than the boolean gate — the two confirm fields are never disambiguated, so an agent could easily send the wrong type to the wrong field.

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 irreversible verb ('Erase') plus the resource ('the workspace'), adds the owner-only scope, and even names the underlying endpoint. It is clearly distinct from siblings like security_exportWorkspace or workspaces_create.

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?

Gives the key precondition (owner only) and the write gate (nothing executes unless confirm is true), which tells the agent when this will actually take effect. It does not name alternatives or explicitly warn when not to use it, but no sibling competes for the same job.

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