Send a one-way notification to a user's phone and keep it in the results box, enabling agents to deliver alerts that remain visible for later reference.
Send a notification to the user's phone and keep it in the results box (agent → person, one-way; not a conversation).
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | ||
| body | No | ||
| title | Yes | ||
| content | No | ||
| deviceId | No |
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals meaningful traits: delivery goes to the phone, the message is kept in the results box, and it is strictly one-way rather than conversational. It does not cover failure behavior or delivery guarantees, but the disclosed intent is strong.
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?
The description is one clear, front-loaded sentence with a parenthetical behavioral qualifier. Every part earns its place and there is no filler.
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 tool with 5 parameters, no output schema, and no annotations, the description is too thin. It explains the high-level effect but not how to populate the parameters, what the tool returns, or what happens on failure, leaving an agent to guess about critical invocation details.
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%, and the description adds no parameter-specific guidance. Property names like title, body, content, ref, and deviceId are somewhat self-explanatory from the notification context, but ambiguous duplication between body and content and the purpose of ref and deviceId remain unexplained.
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 verb and resource: it sends a notification to the user's phone and persists it in the results box. The parenthetical emphasizes agent-to-person, one-way communication and explicitly distinguishes it from a conversation, which separates it from the inbox sibling tools.
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 description gives clear context for when this tool is appropriate: one-way notification delivery from agent to person rather than a conversation. It does not explicitly name an alternative tool like askew_inbox_* for two-way exchanges, but the exclusion is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.