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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the default-off state, the authorization requirement ('Owner only'), the fallback that a text alert fires when a transfer fails, that suggested words are never auto-enabled, and the invariant that on_call_phone must not be the shop's own number. It stops short of stating what turning 'on' off does to existing words or transfer settings, or any rate/pagination concerns.

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 enumeration is front-loaded after a one-line purpose statement and every clause maps to a distinct behavior, but the middle section is a dense run-on of semicolon-chained parentheticals that takes effort to parse.

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 six-parameter configuration tool with an output schema and no annotations, this covers the essentials: defaults, side effects, auth level, cross-tool dependency on schedule.addOpenSlots, and a validation rule on the phone number. Minor gaps remain around disabling behavior and the interaction with the voice-AI/route settings, but nothing critical to a correct call is missing.

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 0%, so the description must teach all six parameters — and it effectively does: 'on' enables it, 'words' are the shop's own trigger words (with suggested_words explicitly not applied), 'transfer' routes to on_call_phone, 'text_alert' sends a summary plus callback number, and 'on_call_phone' is a worker phone that must differ from the shop's number. This adds genuine meaning well beyond the bare types in the schema.

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?

Opens with a scoping sentence ('How the shop's voice agent handles emergency calls') and then enumerates the specific settings it controls (on, words, transfer, text_alert). It is clearly distinguishable from siblings like phone_setVoiceAi or phone_setRoute by the emergency-call focus, though the actual verb ('configure/set') is never stated outright.

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 real operating context: off by default, words must be the shop's own triggers, transfers route to on_call_phone, and emergencies can only be booked into slots opened via schedule.addOpenSlots with kind emergency. It never explicitly contrasts itself with the sibling phone_emergency or phone_setVoiceAi, so an agent must infer the selection boundary.

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