control_msg

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

No annotations are provided, so the description carries the full burden. It usefully discloses that this is a single-snapshot view of the most recent message (not a stream or history) and that the payload is raw. However, it says nothing about behavior when no message has arrived yet, whether reads consume the message, or what authority is needed.

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?

A single short fragment with the core identifier and return fields front-loaded, and the "debug only" caveat trailing. Nothing is padded, though the telegraphic style borders on cryptic.

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 zero-parameter debug tool this is mostly sufficient: the return fields are described in lieu of an output schema. It is still missing the empty/no-message case and whether repeated calls return the same message, which matter for a snapshot-style debugger.

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 tool takes zero parameters, so there is no parameter meaning to convey; the baseline for a parameterless tool applies cleanly.

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 names a specific resource — the last raw server message — and enumerates its shape (id, length, hex), which distinguishes it from siblings like control_state or control_wait_prompt that deal in parsed state or prompts. It is a noun phrase rather than an explicit verb, but the retrieval intent is 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?

"debug only" gives a clear usage context and an explicit exclusion, telling the agent not to route normal gameplay/state inspection through this tool. It does not name an alternative (e.g., use control_state for parsed state), which is the only thing separating it from a 5.

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