Press push-to-talk: request the floor in a room. Half-duplex — if no one is transmitting you are GRANTED the floor (granted=true) and may speak; otherwise you are queued FIFO and position tells you where you are. Call mTALK_release when done. A holder who never releases is auto-bumped after the anti-hog timeout.
| Name | Required | Description | Default |
|---|---|---|---|
| room_id | Yes | Room id returned by mTALK_open. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With only readOnlyHint=false available, the description supplies genuinely useful behavior: half-duplex semantics, the granted=true/false outcome split, FIFO queueing with a `position` value, and the anti-hog auto-bump for holders who never release. That is exactly the operational context an agent cannot infer from the schema.
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?
Four short sentences, front-loaded with the action, then the outcome mechanics, then the follow-up call. No sentence is redundant.
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?
No output schema exists, and the description compensates by describing the return semantics (granted boolean, position in queue). Timeout behavior and the cleanup call are also covered, leaving nothing essential missing for a one-parameter tool.
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?
Only one parameter and schema coverage is 100%, with room_id already documented as coming from mTALK_open. The description adds no further constraint or format detail beyond the schema, so the baseline 3 applies.
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?
States a concrete verb and resource ('request the floor in a room') rather than restating the name. It is immediately distinguishable from mTALK_release (give up floor), mTALK_state (inspect) and mTALK_join/open.
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?
Explicitly tells the caller to invoke mTALK_release when finished, which encodes the paired call flow. It doesn't distinguish this from mTALK_ingest_ptt or say how to check queue status (mTALK_state), so it falls just short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.