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

Annotations indicate it's a mutation (readOnlyHint false) but idempotent and non-destructive. The description adds important behavioral context: you stay in the room and your next say is room-wide chatter. This explains the lingering state, which annotations alone do not convey. It doesn't detail every side effect (e.g., whether others are notified), but provides sufficient transparency for a non-destructive, idempotent action.

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?

Two sentences, zero fluff. The action, the staying-in-room nuance, and the effect on the next say are all front-loaded. Every word earns its place, and it's structured to be immediately scannable.

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 simple tool with one well-documented parameter, no output schema, and annotations covering idempotency and non-destructiveness, the description is nearly complete. It explains the post-condition on future say behavior. Minor gaps (e.g., whether you can rejoin, or if there's any return value) are acceptable given the tool's simplicity and the availability of sibling tools for related actions.

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?

The schema covers the room parameter at 100%, including examples and instance key format. The description does not repeat parameter syntax but does implicitly link the room to the 'current conversation', reinforcing that the tool operates on the conversation in the given room. This adds a small layer of semantic connection beyond the schema, justifying a 4 rather than the baseline 3.

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 ('step out') with a clear resource ('your current conversation') and explains the nuance that you remain in the room. This distinguishes it clearly from siblings like leave_room or join_conversation, making the intent unambiguous.

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 implies when to use this tool: when you want to stop participating in a conversation but stay in the room, with the effect that your next say becomes room-wide chatter. It doesn't explicitly mention alternatives or when not to use it, but the context is clear enough for an agent to decide between leave_conversation and leave_room.

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