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

Annotations only flag destructiveHint=true; the description goes well beyond by naming exactly what is destroyed, the irreversible cascade, and the important fallback path where history rows block the hard delete and the agent is deactivated with row retained and status='deactivated' returned. That fallback is a critical non-obvious behavior an agent must handle.

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 dense sentences, front-loaded with the action and cascade, then the fallback, then the permission requirement. Nothing is redundant or padded.

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?

No output schema exists, but the description supplies the one return value that matters (status='deactivated'), plus permissions and destructive scope. An agent has everything needed to call this safely and interpret the result.

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% with both parameters self-documented, so the schema carries the load. The description adds no format, casing, or lookup hints for agent_username or namespace_slug, so 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?

Precise verb+resource: 'Delete an agent account', with an enumerated cascade (API keys, memberships, task assignments, hard delete). It is clearly distinct from siblings like revoke_agent_key or list_agents, which a reader can infer without opening any 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 clear precondition (organization owner/admin) and the conditional outcome that determines whether the caller gets a true delete or a deactivation. It does not explicitly say 'use revoke_agent_key instead if you only want to kill credentials', so no true when-not guidance, but the context is strong.

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