Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) by disclosing the ~30s wait ceiling, the status values that require polling, the 2000-character (~2 min speech) input cap, the setup_required failure mode, and the fact that the hosted server cannot read the local config file. This is real operational context an agent needs.

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 core action and its return are front-loaded in the first sentence, and every subsequent sentence carries distinct operational detail. It is dense and slightly sprawling with parentheticals, but no sentence is 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?

With no output schema and no annotation-level detail on returns, the description supplies the success statuses, the polling fallback, and the setup_required path. It stops short of describing timeout/error behavior when the human never answers, which is the one remaining gap for a 4-parameter outbound-call tool.

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 carry the load, and it explains `question` (spoken verbatim, up to 2000 chars, not necessarily interrogative), `to` (a Call Me app number sourced from config), and `session_token` (thread continuity). Only `from_label` is left unexplained, so it nearly compensates for the coverage gap.

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 concrete verb and resource chain: ring the human's iPhone, read `question` aloud, return their reply. It also names the follow-up sibling (poll_result) and the alternative content types, so an agent can distinguish it from text/wait_for_reply without opening a 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?

Explicit routing: use poll_result when the result status is "ringing" or "in_call"; read `to` from ~/.aiphone/config.json when running locally; pass a prior session_token to stay in the same thread; expect setup_required with an App Store link if unconfigured. When-to-use and what-to-do-next are both spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.