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

Annotations declare destructiveHint=true and non-idempotent, but the description adds critical behavior beyond them: the preview-first default, the owner-only authorization requirement, and precisely what is destroyed (story/collaboration records) versus preserved (world/library assets). This is exactly the kind of destructive-scope detail an agent needs.

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 tightly packed sentences with the default behavior front-loaded, then the constraint, then the escalation path. Every sentence carries load-bearing information; 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?

For a destructive mutation with no output schema, the description covers the safety profile, authorization, destruction scope, and the confirmation workflow. An agent has everything needed to invoke it correctly and safely.

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 each parameter is already documented, setting a baseline of 3. The description adds workflow-level meaning by specifying the sequencing and the requirement that expected_title come from the preview, which the schema field alone states more narrowly.

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 ('Delete') and resource ('Creator Flow Project'), and immediately scopes it as a preview-by-default, owner-only operation. This clearly distinguishes it from sibling deletes like delete_world and delete_world_asset by naming the record types affected (story/collaboration) and preserved (world/library assets).

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 an explicit two-step protocol: keep dry_run=true until the user approves the stated impact, then set dry_run=false, confirmed=true, and expected_title from the preview. It names the exact conditions and parameter states that gate the dangerous call, 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.