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

Annotations already flag destructiveHint=true and non-idempotent, so safety is covered; the description goes further by stating what is destroyed, that credits survive, that the operation is irreversible, and that owner permission is required. These are real behavioral facts not present in the structured fields.

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?

Front-loaded with "Permanently deletes", then scope, then caveats, then confirmName semantics, then irreversibility. Dense but nearly every clause carries operational weight; the long compound first sentence could be split, but nothing is padding.

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 single-parameter, no-output-schema destructive tool, the description covers scope, permissions, preconditions, parameter acquisition, and irreversibility. An agent has everything needed to call 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 the baseline is 3, but the description adds meaning the schema lacks: the value must match the project name exactly as the user typed it and must come from the user rather than the agent. That is a substantive constraint on how to obtain the parameter.

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?

"Permanently deletes the current project and everything in it" names a specific verb, resource, and cascade scope, and immediately enumerates what falls under that scope (posts, accounts, knowledge, workflows, campaigns, API keys). This clearly separates it from narrower siblings like delete_campaign, delete_post, delete_knowledge, and delete_workflow.

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 concrete when-not conditions: only the owner may call it, and the target cannot be the sole project, which implicitly routes the agent to check_projects first. It also prescribes a pre-call interaction pattern (warn the user, have them type the name). It stops short of naming an explicit alternative tool or what to do when the caller is not the owner.

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