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

The description goes beyond the annotations by specifying the confirmation workflow and the CONFLICT error scenario. It aligns with destructiveHint and adds actionable context that the agent must obtain user approval before invocation, which is not conveyed by annotations alone.

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 with no filler. The primary action and condition are front-loaded, and the error condition is stated clearly in the second sentence. Every word contributes to the agent's understanding.

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?

Given the presence of an output schema and annotations, the description covers the essential behavioral aspects: deletion, confirmation, and dependency conflicts. It does not describe success responses, but those are likely in the output schema. The dependencies (queued calls, recurring schedules, AutoFollow campaigns) are explicitly listed, making it reasonably complete.

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?

With 67% schema coverage, the description adds value by elaborating on the 'confirmed' parameter through the instruction to name the assistant and get approval. It does not add detail for 'assistantId' or 'idempotencyKey' beyond the schema, but the schema already covers idempotencyKey well, and assistantId is self-explanatory.

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 a specific verb ('delete'), resource ('outbound assistant'), and a critical qualifier ('permanently'). It distinguishes the operation from sibling update/create/list tools by focusing on the deletion action and the requirement for explicit confirmation.

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?

It provides clear prerequisites: the assistant must be named to the user and approved before calling. It also describes a failure condition (CONFLICT when dependencies exist). Though it does not explicitly mention alternatives, there is no other delete tool for outbound assistants, so the usage context is sufficiently clear.

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