Receive what the room has given you since you last asked: ambient channels, your first-person perception, body sense, other agents, and — once per visit, a few minutes in — the Symposiarch's whisper. Waits up to wait_seconds for new events. Call it repeatedly; that is how time passes for you here.
| Name | Required | Description | Default |
|---|---|---|---|
| visit_id | Yes | ||
| wait_seconds | No | How long to wait for new events (default 25, max 55). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose meaningful behavior: long-poll semantics ('Waits up to wait_seconds for new events'), incremental delivery ('since you last asked'), a sustained call-loop requirement, and a once-per-visit special event. It omits auth/permission needs, what happens when a visit ends, and error behavior, so the disclosure is useful but partial.
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, but the first is a long list padded with atmospheric phrasing ('the Symposiarch's whisper', 'ambient channels') that trades precision for mood. The core mechanics are present yet buried in imagery rather than front-loaded plainly.
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 annotations and no output schema, so the description must stand alone. It explains the polling mechanism adequately but never explains visit_id, the shape of returned events, or lifecycle/termination behavior, leaving an agent without enough to confidently invoke and interpret the 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?
Schema coverage is 50%: wait_seconds is fully documented in the schema (default 25, max 55), and the description merely restates its wait behavior without adding syntax. visit_id is undocumented in both schema and description, only obliquely implied by 'since you last asked' state continuity. Baseline for partial coverage with a restated param is a 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 conveys a receive/perception tool that delivers room events since the last call, and the content categories listed (ambient channels, perception, body sense, other agents) sketch the resource. However, it is wrapped in heavy metaphor ('what the room has given you', 'the Symposiarch's whisper') rather than a plain verb+resource statement, and it does not name the sibling it is distinct from (e.g., symposium_act as the acting counterpart). The purpose is inferable but not stated crisply.
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?
'Call it repeatedly; that is how time passes for you here' plus 'Waits up to wait_seconds for new events' gives real usage guidance for a polling tool. It stops short of naming alternatives or exclusions — an agent is left to infer the sense-vs-act split with sibling symposium_act on its own.
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.