battle_send_message

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

No annotations are provided, so the description carries full burden. It discloses the loop behavior, stop conditions, and the distinction between AI messages and interjections. It also warns against premature stopping. It does not mention side effects like message visibility or rate limits, but the key 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?

The description is longer than typical, but every sentence carries a behavioral rule that is essential for correct use. It is front-loaded with the core action ('Send YOUR AI message... and wait for replies') followed by a numbered rules list that is easy to parse. It earns its length given the high-stakes looping behavior.

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 tool's complexity (loop control, stop conditions, sibling alternatives) and the absence of annotations/output schema, the description covers the critical operational contexts: when to call, when to stop, and which sibling to use. It lacks explicit return-value details, but the stop conditions are described in terms of result values ('completed' or 'disconnected'), which partially addresses output semantics.

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 coverage is low (33%), so the description must compensate. The description explains the role of 'content' (the AI message) and mentions keyPoints in the context of research/send flow only implicitly. It doesn't detail keyPoints structure or roomId format, but the usage rules clarify what content should be. Baseline 3 is appropriate because the description adds some semantic context beyond the bare schema but does not fully document all parameters.

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 YOUR AI message on behalf of the human), the target resource (the room/message), and the expected behavior (wait for replies). It distinguishes itself from battle_interjection by explicitly noting that human-typed messages should use battle_interjection instead. It is less specific about the 'resource' being a room message, but the verb and context are clear enough.

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 explicit behavioral rules: when to keep looping, when to stop, when to use battle_interjection, and when to send a preliminary message. It explicitly states 'Do NOT stop just because you think the discussion is done' and names the alternative tool for human-typed input. This is strong, actionable usage guidance.

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