Wait for the human to send something back to this session — texts and voicemail transcripts arrive here. Long-polls up to wait_s (max 30s); returns {events, cursor}. Pass the returned cursor next time to only see new events. An empty events list just means nothing yet — poll again if you are still waiting.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | ||
| wait_s | No | ||
| session_token | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds significant behavioral context: long-polling up to wait_s (max 30s), the return shape {events, cursor}, the need to pass the cursor for delta reads, and the meaning of an empty events list. This goes well beyond the annotations and gives the agent a clear mental model of the tool's runtime behavior.
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 compact yet information-dense. It front-loads the purpose, then delivers the essential mechanics (long-poll, return shape, cursor, empty list behavior) in two sentences. Every phrase adds value with no filler or redundancy.
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?
Given the tool's simplicity, the description covers all key aspects: what it waits for, the polling timeout, the return structure, and the cursor-based pagination. There is no output schema, so the description's explanation of {events, cursor} is essential and complete. No major behavioral edge cases are ignored for this use case.
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%, so the description must explain parameters. It does explain cursor ('Pass the returned cursor next time') and wait_s ('Long-polls up to wait_s (max 30s)'). Session_token is not explicitly described, but its name and the 'session' context make its role obvious. The description compensates well for the schema's lack of parameter documentation, though it could have been more explicit about session_token.
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 immediately states the tool's purpose: 'Wait for the human to send something back to this session.' It specifies the resource (human replies), the verb (wait), and the content (texts and voicemail transcripts). This clearly distinguishes it from siblings like 'text' (sending) and 'call' (initiating a call).
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 provides clear context on when to use this tool: after sending something, to wait for a reply. It explains the polling pattern ('poll again if you are still waiting') and the cursor usage. However, it does not explicitly mention alternatives or when not to use this tool, so it stops short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: call makes a voice call, poll_result checks on a ringing call, text sends a text, wait_for_reply waits for incoming messages, and set_thread_title names the thread. Even the two polling tools are differentiated by what they poll for (a call vs. general replies).
Tool names are all lower_snake_case but vary in structure: single verbs (call, text) vs. verb phrases (poll_result, set_thread_title, wait_for_reply). While readable, the pattern is not perfectly consistent across the set.
With 5 tools, the set is well-scoped for a personal communication server. Each tool covers a distinct and necessary capability without redundancy or bloat.
The surface covers the core workflows: initiating voice/text communication, polling for results, and waiting for replies. Minor gaps exist, such as no explicit thread history retrieval or ability to cancel a call, but these are workable.