Receive unacknowledged messages for an agent, optionally long-poll up to 60 seconds, then acknowledge after handling to prevent duplicate work.
Your unacked messages (at-least-once). wait = long-poll seconds (<=60). Ack with msg_ack after handling.
| Name | Required | Description | Default |
|---|---|---|---|
| ack | No | ||
| wait | No | ||
| agent | No | ||
| limit | No | ||
| types | No | ||
| api_key | No |
Changes observed during successful MCP inspections.
v0.36.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does disclose two valuable traits: at-least-once delivery (implying possible duplicates/idempotency needs) and the long-poll cap of 60 seconds. It omits other key behaviors such as what limit/types filtering does, whether the ack parameter auto-acks, or whether an api_key is required, so the disclosure is 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?
Three short fragments, each front-loaded with the highest-value fact (what you get, the polling cap, the ack obligation). No filler, though the extreme terseness leaves little room for the missing parameter guidance.
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 6-parameter tool with zero schema coverage, no annotations, and no output schema, this is under-specified: the ack workflow, limit/types filtering, and auth are all left to guesswork. The delivery-semantics note is valuable but far from sufficient to call this tool confidently.
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 description coverage is 0% across 6 parameters, so the description must compensate and it only covers one: wait, with its <=60 ceiling. The ack, agent, limit, types, and api_key parameters receive no explanation at all, leaving most of the calling surface undocumented.
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?
Names a specific verb and resource ('Your unacked messages') and immediately characterizes the delivery model as at-least-once, which tells the agent exactly what this returns. It does not explicitly differentiate from the close sibling msg_get, so the agent has to infer the boundary between them.
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 workflow instruction 'Ack with msg_ack after handling' gives a clear follow-up action and names the sibling to use next. However it never states when to choose msg_recv over msg_get (the obvious alternative), leaving the core selection decision implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.