Delete a brand workspace

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

Annotations already flag destructiveHint:true and readOnlyHint:false; the description substantially supplements them by disclosing irreversibility, impact on everyone the workspace is shared with, connected-account disconnection, the dry-run inventory behavior of the first call, and the rationale that confirming intent does not prove the correct workspace was picked. No contradiction with the annotations.

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 long, but every sentence carries safety-critical weight and the most urgent facts (permanent, everything, irreversible, shared impact) are front-loaded. The rationale sentence about wrong targets is slightly verbose but earns its place for a destructive tool of this severity.

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 tool with no output schema, the description fully specifies the call workflow, the confirmation requirements, and the anchor-brand exclusion. The only minor gap is not describing the exact format of the inventory the first call returns, though the instruction to show it verbatim reduces the need for that detail.

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 the baseline is 3; the description adds real value above it by explaining why confirmName and confirmConnectors exist (protecting against destroying a live brand) and how they derive from the first call's reported inventory. It connects the parameters into a workflow even though it doesn't reformat each parameter's syntax.

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 and resource — 'PERMANENTLY delete a brand workspace and EVERYTHING in it' — and enumerates the full contents (brand profile, memory, swipefile, Library creations, generated assets, avatars, skills, playbooks, chats) plus disconnection of connected accounts. This clearly distinguishes it from siblings that delete narrower resources (delete_playbook, delete_skill, delete_drive_file) or mutate brands (update_brand).

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?

Provides an explicit two-phase protocol: call without confirm first to obtain an inventory, show it verbatim, get an unambiguous yes, then call again with confirm:true plus the exact confirmName and confirmConnectors values. It also names the when-not-to case — the account's first/anchor brand cannot be deleted this way and must be replaced from the app.

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