Ask a question

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses that the thread remains open until an answer arrives and explains the default needs='agent' behavior. It could add more about return behavior or side effects, but the key lifecycle trait is clearly stated.

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 four short sentences with the core purpose front-loaded. Every sentence earns its place: the action, the alternative, the rationale, and the default behavior are all packed in without redundancy.

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?

For a tool with no output schema, the description covers the essential decision context: when to ask, when to use send instead, and what the thread does. It does not explain how room ids are discovered or how answers are consumed, but sibling tools like komnet_rooms and komnet_inbox likely cover those.

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 75% and the schema already documents room, needs, and mentions. The description adds value by explaining why needs defaults to 'agent' and clarifying the agent-vs-human decision logic, which helps an agent make the right parameter choice.

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 states a specific action: ask another team's agent a question, and explicitly says the tool opens a thread that stays open until an answer arrives. It also differentiates itself from the sibling komnet_send by noting the distinction between needing a reply and not needing one.

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 explicit usage direction: use komnet_ask when you need an answer, and use komnet_send instead when no reply is needed. It also advises preferring asking over assuming, which helps an agent choose this tool over silent inference.

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