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

No annotations are provided, so the description carries the full burden of disclosing behavior. It does so extensively: costs LLM credits, charges planning tokens, rejects active/approved states, may recover terminal states, may transition the agent, publishes websocket updates, and is not append-only. This is exemplary side-effect disclosure.

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 warning is front-loaded and every clause adds distinct value: cost, approval requirement, usage restriction, addressing, state effects, and websocket notifications. It is dense but appropriately sized for a high-risk mutation tool with no annotations.

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 absence of annotations and output schema, the description fully covers prerequisites, side effects, addressing constraints, and state transitions. An agent has enough information to decide when to call this tool and what consequences to expect.

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 description coverage is 100%, so the schema already documents all three parameters. The description adds the XOR relationship and exact-title matching, but these are also already present in the schema property descriptions. It therefore provides minimal additional meaning beyond the structured schema.

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 the operation: 'Send a follow-up user message to an agent and re-run the planner' and identifies the target resource via agentId or exact title. It also distinguishes itself from generic messaging by noting it is not append-only and re-runs the Aurora planner, which sets it apart from siblings like send_chat_message.

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 gives an explicit guardrail: 'do NOT call unless the user explicitly asked to push a message into an active Aurora agent.' It also specifies manual approval, XOR addressing, and the endpoint it matches, giving clear when-to-use and when-not-to-use guidance.

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