Phone Start

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

No annotations are provided, so the description carries the burden and does well: it declares idempotency, discloses that relayed audio keeps playing with the phone's screen off, that inputs are stamped with the bar heard, and that no set is started and no sound is played locally. It also discloses network exposure (tailnet) and return behavior (the address). It omits failure modes such as port-in-use or what happens if no live engine is running.

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?

Front-loaded with the verb and purpose, and every sentence adds information (idempotency, stream behavior, inbox, return, follow-up). It is dense and jargon-heavy ('the newest live engine's master', 'tailnet'), which slightly increases parsing cost 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?

An output schema exists, so return values need not be explained in depth, and the description still notes 'Returns the address to give them'. It covers the stream, input path, and follow-up tools; the only gap is the unexplained port parameter for a network-listening server.

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 compensate. It does explain 'inbox' fully (what gets written, default path 'the playing engine's <project>/notes/phone_inbox.jsonl'), but the 'port' parameter is never mentioned and its role must be inferred from 'page server'. Partial compensation only.

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 specific verb and resource (start the phone page server) and immediately scopes it: relays the newest live engine's master as an mp3 stream, accepts taps/voice notes. It explicitly distinguishes itself from siblings with 'Never starts a set or plays sound here', separating it from live_start/stream_start, and directs reads to phone_listen.

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?

Clear when-to-use context (the live set in the person's pocket over the tailnet) and it names an alternative for the follow-up action ('Read what they send with phone_listen, or watch the inbox file'). It also declares an important exclusion ('Never starts a set or plays sound here'). It does not explicitly contrast with phone_stop/phone_restart/stream_start, which would have made it a 5.

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