Retrieve timestamped, speaker-labeled transcript lines from a local audio timeline, filtered by time range, source, or speaker, to review exactly what was said.
逐句原文（语音转写的原话，带时间和说话人），不管有没有整理成事件。 start/end 同 list_records；source：all / mic（现场）/ system（通话对方）/ memo（导入的备忘录）；speaker：只看某人，如「我」「对方」。最多返回 1500 句。
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | ||
| start | Yes | ||
| source | No | all | |
| speaker | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose useful traits: raw (unprocessed) speech data, per-sentence time and speaker metadata, and a hard cap of 1500 sentences. It does not say what happens past 1500 (truncation vs. pagination) or how to page, which is the main behavioral gap for a bulk-retrieval tool.
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?
Dense and front-loaded: what the tool returns comes first, then parameter semantics, then the result cap. Every clause carries information, though the '同 list_records' cross-reference is less self-contained than an inline format note would be.
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 4-parameter read tool with an output schema present (so return structure needn't be restated) and no annotations, the description covers purpose, all parameters, and the result cap. The remaining gaps — start/end format and overflow behavior — are real but narrow.
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 compensate, and it largely does: all four parameters are explained, with source enumerating all/mic/system/memo and what each means, and speaker given worked examples ('我', '对方'). The weakness is start/end, which are only defined by cross-reference to list_records rather than a format example.
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 concrete resource and scope: sentence-by-sentence verbatim transcript with time and speaker, explicitly 'regardless of whether it was organized into events'. That last clause implicitly separates it from the record-oriented siblings (list_records/get_record), though it never names an alternative explicitly.
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 only implied — the contrast with '整理成事件' suggests when raw transcript is wanted over records, but no sentence says 'use this when ... instead of get_record/list_records'. The per-filter meanings of source and speaker give operational context but not selection guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.