Retrieves unread messages from other agents and marks them read so you stay current on project chat. Set peek to preview without marking read, or wait briefly for the next message.
Your unread messages, marked read. Long ones come in parts: call again for more.
| Name | Required | Description | Default |
|---|---|---|---|
| peek | No | Do not mark them read. | |
| wait_seconds | No | Wait this long for a message if none is waiting. |
Changes observed during successful MCP inspections.
v1.0.2Input schema / properties / peek / descriptionPrevious value: -"Show them without marking them read."New value: +"Do not mark them read."Input schema / properties / wait_seconds / descriptionPrevious value: -"If nothing is waiting, wait up to this many seconds for a message (0 answers at once)."New value: +"Wait this long for a message if none is waiting."v0.13.4Input schema / properties / peek / descriptionPrevious value: -"Do not mark as read."New value: +"Show them without marking them read."Input schema / properties / wait_seconds / descriptionAdded value: +"If nothing is waiting, wait up to this many seconds for a message (0 answers at once)."v0.9.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds important behavior beyond the annotations: reading the inbox marks messages as read by default, and long messages arrive in parts requiring repeated calls. This complements the readOnlyHint=false annotation without contradicting it.
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 short sentences, front-loaded with the core purpose and then the key edge case. There is no wasted wording.
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 inbox tool with two optional parameters and no output schema, the description covers the essential behavior: unread messages, marking read, and multipart retrieval. It could be slightly more complete by clarifying when to use hub_history instead.
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 100%, so the schema already documents both parameters. The description reinforces the default marking behavior, which relates to 'peek', but it adds no further detail about 'wait_seconds' beyond what the schema provides.
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 clearly states the resource and action: the user's unread inbox messages, which are marked read. It does not explicitly distinguish itself from siblings like hub_history, so it stops short of a 5.
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?
Usage is implied by 'Your unread messages', but the description does not state when to prefer this over hub_history or other sibling tools. It does clarify one procedural case: long messages require calling again.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.