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

Annotations already flag destructiveHint=true, but the description adds substantive behavior: the delete is cascading ("everything in it"), has downstream effects ("Flows that search it will find nothing"), and may short-circuit into an approval flow returning needs_confirmation. That is exactly the extra context a destructive tool's annotations cannot convey.

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 action and its scope before the cautionary guidance. The parenthetical "(the user knows; the KB page in Workbench lists them)" is slightly clunky but earns its place by telling the agent where the consumer list lives.

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 no-output-schema destructive tool, the description covers scope, downstream impact, and the confirmation handshake, which is most of what an agent needs. It omits whether deletion is permanent/irreversible and what permissions are required, leaving a small but real gap.

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 kbId, workspace, and approvalId are all documented in the schema itself. The description only indirectly gestures at approvalId via "May return needs_confirmation"; it adds no format or constraint detail, so the baseline 3 applies.

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+resource ("Deletes a knowledge base") and immediately scopes the blast radius ("everything in it"), which distinguishes it from the sibling workbench_kb_document_delete that removes a single document. An agent can identify the operation without opening the schema.

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 a concrete precondition — check which agents use the KB and warn the user before proposing deletion — plus the confirmation path ("May return needs_confirmation"). It does not explicitly contrast against sibling alternatives such as workbench_kb_document_delete, so it stops short of full when/when-not routing.

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