Ring the human's iPhone, speak the question aloud, and return what they
say. Waits up to ~30s; if the result comes back status "ringing", follow up
with poll_result. to is their 10-digit /call-me number (from the /call-me
iOS app — not a real phone number). Pass a previous session_token to stay
in the same thread on their phone.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | ||
| question | Yes | ||
| from_label | No | Someone's AI | |
| session_token | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds important behavioral context beyond annotations: waits up to 30 seconds, returns a status that may be 'ringing', and the `to` number is a special /call-me number, not a real phone. While annotations already indicate non-read-only and destructive, this description enriches understanding of side effects.
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 concise and structured effectively, with three sentences covering purpose, behavioral details, and parameter nuances. Each sentence adds value without 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?
The description covers the essential aspects: action, waiting time, status handling, the special `to` number, and session token. It lacks details about the exact return format and the `from_label` parameter, but these are relatively minor given the tool's straightforward nature.
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?
The schema has 0% description coverage, so the description must explain parameters. It clarifies `to` and `session_token` well, and `question` is inferable from the tool's purpose. However, `from_label` is not explained, leaving a gap in parameter semantics.
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 tool's function: ringing the human's iPhone, asking a question aloud, and returning their response. It uses a specific verb and resource, and is distinct from siblings like text or poll_result by describing the spoken interaction.
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?
Provides clear guidance on when to use the tool and next steps: it specifies following up with poll_result if the status is 'ringing' and explains the nature of the `to` number and session_token. However, it does not explicitly contrast with all sibling tools or state when not to use it.
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.