Phone Hum

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

With no annotations the description must carry the full burden, and it does disclose real behavior: detection works both from the note's acoustic character (pitched, held notes, few words) and from inbox kind 'hum', and every note retains a reference master file (<id>_ref.wav, 3 s before to 2 s after, with beat stamps). What it never states is whether the call is read-only or writes/regenerates artifacts, or any cost/permission implications.

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 question form front-loads the purpose well, but the remainder is one dense, metaphor-laden run of clauses ('the music bleeding into the mic lines the note up with the beat he heard') where plainer wording would be shorter and clearer. Nothing is padded, but the signal-to-noise ratio is mediocre.

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 spelled out, and complexity is low (one optional param). The description covers purpose and output artifact naming, but leaves the read-vs-write nature and sibling routing unaddressed, which are the gaps that matter for a phone-analysis tool with no annotations.

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% and the single parameter has no description, but the prose partially compensates by explaining that omitting voice_id targets the latest note. It does not say where a voice_id comes from or what form it takes, so an agent still has to guess how to address a specific note.

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 opening clause states a specific analysis task: decide whether a voice note is a hum versus a sung line, and locate the reference music underneath it. This is distinctive from siblings like phone_listen or analyze_voice_heard, though the tool is never named against them and the phrasing ('the music he heard', 'the page played under it') is idiosyncratic enough to slow an agent down.

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?

The only routing hint is the parenthetical 'any note (the latest when no voice_id)', which addresses target selection rather than when to choose this tool. There is no statement of when not to use it and no mention of the many nearby alternatives (analyze_voice_heard, phone_listen, tell_heard) that an agent would have to weigh.

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