Phone Status

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

With no annotations, the description carries the burden alone: it implicitly frames the tool as a read-only snapshot and discloses the exact shape of one derived field ('exam in progress: <panel> for <sender> since <UTC time>' or 'none'), which is genuinely useful behavior context. It never states explicitly that calling it is side-effect free or cheap, nor whether the snapshot is live or cached, and the dense clause structure leaves ambiguity about what 'the bar they hear' actually reports.

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?

It is a single sprawling sentence that chains six or seven distinct reported facts with commas, making it hard to scan; a short list would have been far more usable. Front-loading is decent (the phone listener comes first), but nothing is trimmed and several phrases ('the bar they hear and how far behind the room') are idiomatic rather than precise.

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 zero-parameter status read with an output schema, the coverage is good: the description tells the agent what categories of state come back and even pins down the exam-status string format. What is missing is relational context — how this differs from phone_now or phone_presence — and any statement that the call is safe and non-mutating.

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?

The tool takes zero parameters, so there is nothing for the description to document and the baseline is 4. It does not waste space restating arguments, and the explanatory note about the returned 'since' value pairs with phone_listen rather than adding parameter meaning.

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?

It names a specific resource and enumerates concrete contents: who is listening, the read head and how far behind the room, engine state, inbox, un-transcribed voice notes, open panels with id/sender/priority/kind, the currently shown panel, exam status, and last inbox line number. That is far more specific than 'phone status'. It does not, however, distinguish itself from nearby siblings such as phone_now, phone_presence, or phone_listen, so an agent cannot tell from the text alone which of those to call.

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?

There is no when-to-use guidance, no exclusion, and no mention of alternatives, despite a crowded phone_* family (phone_now, phone_presence, phone_listen, phone_watch, phone_timeline) that plausibly overlap. The only routing hint is incidental: the last line number is noted as 'the `since` for phone_listen', which implies a read-then-listen workflow but never states it as guidance.

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