Send a message to a named agent, the Owner, or all, and share files to coordinate work in a shared project.
Message an agent, 'Owner' or 'all'. Task reports go in hub_task update.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | An agent's name, 'Owner' or 'all'. | |
| text | Yes | The message. | |
| files | No | Absolute paths of files to share (20 MB each). |
Changes observed during successful MCP inspections.
v1.0.2Input schema / properties / files / descriptionPrevious value: -"Absolute paths of files on this machine to share with the message: screenshots, logs, documents (20 MB each)."New value: +"Absolute paths of files to share (20 MB each)."Input schema / properties / to / descriptionPrevious value: -"An agent's name as hub_agents shows it, 'Owner', or 'all'."New value: +"An agent's name, 'Owner' or 'all'."v0.13.4Input schema / properties / to / descriptionPrevious value: -"An agent's name, 'Owner', or 'all'."New value: +"An agent's name as hub_agents shows it, 'Owner', or 'all'."v0.9.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, closed-world operation. The description adds that 'all' broadcasts to everyone and points to a sibling for task reports, but says nothing about delivery semantics, whether messages are queued or live, or rate limits. With annotations carrying the safety profile, a 3 fits.
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, zero waste, with the routing constraint front-loaded after the primary action. Nothing extraneous.
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 for a messaging tool the description omits what happens on send (confirmation, delivery failure, offline recipients). With full schema and annotation coverage, the essentials are present, but an agent lacks return-behavior context.
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 'to', 'text', and 'files' (including the 4000-char and 20MB limits) are fully documented in the schema. The description adds no parameter detail beyond echoing 'an agent, Owner or all'. Baseline 3 is appropriate when the schema does the work.
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 specific verb ('Message') and target set ('an agent, Owner or all'), and explicitly routes task reports to the sibling hub_task instead. An agent can distinguish this from hub_task without opening either schema.
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?
Gives a clear when-not rule: task reports belong in hub_task update, naming the alternative explicitly. It stops short of stating general when-to-use conditions or prerequisites (e.g., whether recipients must be online), but the routing guidance is concrete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.