phone_audio

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

With no annotations, the description carries the full burden and does well: it discloses the 30-second lookback window, enumerates concrete failure modes ('listening off, the app not sharing, no Wi-Fi'), and warns that the transcription is unreliable ('partial or misheard'). It does not cover latency, whether repeated calls return the same window, or privacy implications, which keeps it from a 5.

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?

Two short sentences, front-loaded with the return meaning and followed by the failure/accuracy caveat. Every clause earns its place, including the parenthetical examples that make the scope concrete.

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 one-parameter, no-output-schema tool, the description does the essential work of explaining what a successful result means (transcribed words) and what an unsuccessful one means (a stated reason). Only minor gaps remain, such as result timing or how partial transcriptions are marked.

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 100% and there is only one optional parameter ('device', documented in the schema as a board id needed only with several boards), so the structured field already does the work and the baseline of 3 applies. The description adds nothing about device selection, but nothing is missing either.

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 names a specific resource ('what the iPhone played in the last 30 s') and states the output form ('as words, or why it can't be heard'), which is far more specific than a name restatement. It doesn't explicitly distinguish itself from any sibling, but the audio-capture verb is unique among the listed tools, so an agent can identify it without opening the 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?

Usage is implied by the 30-second window and examples ('a video, a call, an app's voice'), which suggest this is the tool for inspecting recent playback. There is no explicit when-to-use framing, no statement of when not to use it, and no pointer to any alternative for longer history or other audio needs.

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