Send a message to a T3 thread

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

With no annotations provided, the description takes on the full burden of disclosing behavior. It reveals that the tool starts an agent turn, reuses existing settings unless overridden, queues messages if the agent is busy, and returns immediately. It could also mention potential errors or authentication requirements, but the core behavioral traits are well covered.

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 sentences, all information-dense with no fluff. The most important facts (send, start turn, return behavior) are front-loaded, and the later sentences provide necessary behavioral details without repetition.

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?

Since there is no output schema, the description appropriately explains the return behavior: 'Returns immediately; use wait_for_turn or get_thread to see the reply.' It also covers the queuing behavior and parameter inheritance, making it complete for an AI agent to use correctly without requiring external context.

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 75%, so some params (message, threadId, runtimeMode) are already described. The description adds value by explaining that runtimeMode and interactionMode are overrides of the thread's current settings ('unless overridden'), which is not obvious from the bare enum names. It also clarifies that the thread must be existing, reinforcing threadId semantics.

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 action: 'Send a user message to an existing thread and start an agent turn.' This distinguishes it from create_thread (new thread), wait_for_turn, and get_thread (retrieving replies). It uses a specific verb and resource, making the purpose unmistakable.

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 explicitly mentions when to use the tool (to send a message to an existing thread) and provides alternative tools: 'use wait_for_turn or get_thread to see the reply.' It also explains the queuing behavior when the agent is mid-turn, giving clear context without needing to list every sibling.

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