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

The description explicitly discloses the destructive side effect: 'Cascades to attached addresses, email identities, and phone identities.' This, combined with the destructiveHint annotation, fully informs the agent of the operation's impact.

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 two sentences, direct, and free of fluff. It front-loads the main action and then adds necessary context about cascade effects. Every word serves a purpose.

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 delete operation, the description covers the essential context: what is deleted, why you would use it, and what else is affected. The lack of an output schema is acceptable since delete operations typically return a confirmation or empty response. No critical information is missing.

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?

The only parameter 'id' is described as 'Agent ID', which is sufficient given the tool's singular purpose. While terse, it is unambiguous and matches the schema. A bit more detail about the ID format (e.g., UUID) could add value, but it is not necessary for correct invocation.

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?

The description clearly states that the tool deletes an agent by ID, which is a specific action on a specific resource. It distinguishes itself from sibling tools like agent_create, agent_get, agent_list, and agent_update by the verb and intent.

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?

The description provides guidance on when to use the tool ('to remove deprecated or compromised agents that should no longer send messages'), which helps the agent decide when this operation is appropriate. It stops short of explicit warnings or conditions, but the usage context is clear.

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