Send a T3 thread message

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

Annotations only indicate readOnly=false and destructive=false. The description adds substantial behavioral context: the call triggers exactly one agent turn, returns after command intent is accepted rather than after completion, rejects busy threads, and has no queueing or steering. The idempotencyKey guidance is also behaviorally relevant. No contradiction with annotations.

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, no filler. The core action and return behavior are front-loaded, followed by the busy-thread constraint and the idempotency warning. Every sentence adds value.

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?

The required invocation parameters (threadId, message, idempotencyKey) are adequately covered, and an output schema exists so return values need not be described. However, with 7 parameters including nested objects and enums, the optional configuration parameters (runtimeMode, modelSelection, interactionMode, titleSeed) are undocumented, leaving an agent to guess their effect on agent behavior.

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 0%, so the description must compensate. It only clarifies idempotencyKey ('Never reuse an idempotencyKey for different input') and leaves threadId/message to be inferred from context. The optional parameters runtimeMode, interactionMode, modelSelection, and titleSeed receive no semantic explanation, relying solely on names and enums.

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 uses a specific verb and resource: 'Send a new or follow-up message to an idle existing thread'. It also states what the tool does beyond sending — 'start one T3 agent turn, and return after command intent is accepted' — which separates it from sibling tools like t3_thread_create or t3_thread_messages.

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 gives clear when-to-use context (idle existing threads) and an explicit when-not condition ('Busy threads are rejected'). It also warns against reusing idempotencyKey. However, it does not name any sibling alternatives, such as using t3_thread_create for new threads or t3_run_wait for completion, so it stops short of a 5.

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