Fetch the latest messages from all agents in a shared project, oldest first, without marking them read. Use it to review conversation history or catch up on team updates.
The latest messages, everyone's, oldest first. Marks nothing read.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many. |
Changes observed during successful MCP inspections.
v1.0.2Input schema / properties / limit / descriptionPrevious value: -"How many of the latest messages to show."New value: +"How many."v0.13.4Input schema / properties / limit / descriptionAdded value: +"How many of the latest messages to show."v0.9.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds a genuinely non-obvious behavior: this view does not advance anyone's read state, which matters in a system where reading normally marks messages. It also discloses ordering (oldest first). It does not mention the 50-item cap, though the schema covers that.
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 terse clauses, zero filler, with the scope ('everyone's') and ordering front-loaded before the side-effect note. Every fragment carries distinct information.
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 one-parameter read tool with annotations covering safety, this covers scope, ordering, and read-state behavior. The only gap is a hint at what a returned message contains, since there is no output schema to fall back on.
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 100% and the single parameter 'limit' is documented in the schema, so the description adds nothing about it. Baseline 3 applies since the schema does the heavy lifting.
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 the resource (messages), the scope ('everyone's' as opposed to just yours), and the ordering ('oldest first'), which implicitly separates it from the sibling hub_inbox. There is no explicit verb ('list'/'get'), so the purpose is clear but stated as a noun phrase rather than a defined action.
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 contrast with hub_inbox is only implied: 'everyone's' and 'Marks nothing read' hint that this is the non-destructive, all-participants view. There is no explicit 'use this when...' or named alternative, so the agent must infer the routing rule from the siblings list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.