Skip to main content
Glama

aw.speech.transcript.read

Read-only

Read CURRENT accepted original transcript segments and exact time values, explicitly, in bounded pages. Null transcript selects current state; an expected handle fences stale/cleared/newer results. No model I/O, recording or unfinished text. Remote selected transcript text is returned only by this explicit read. Empty state is useful; no editing or calibrated alignment claim. Same session/source epoch/engine/expiry/privacy bounds.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session": "<session>"
    },
    "name": "aw.speech.transcript.read"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
sessionYesPrivate short-lived session capability returned by aw.session.open. Never publish or log it.
transcriptNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnly/non-destructive/closed-world, and the description still adds substantive behavior: paging bounds, handle-based staleness fencing (stale/cleared/newer), the usefulness of an empty state, and the privacy/epoch/expiry bounding of results. What it omits is the failure behavior when the supplied handle is rejected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose well and avoids filler, but the register is telegraphic and jargon-dense, and the trailing fragment "Same session/source epoch/engine/expiry/privacy bounds." is cryptic without antecedent. It reads more like compressed spec notes than an agent-facing instruction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema the description must convey return shape; it does say segments and exact time values are returned in bounded pages, and clarifies that only this explicit read returns remote transcript text. Still missing is what a page actually contains, ordering guarantees, and the behavior on a fenced/stale handle.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only session is documented), so the description must carry weight; it does explain the transcript parameter's null-vs-handle semantics well beyond the schema. Limit and offset get only the vague phrase "bounded pages" and no explanation of the offset ceiling or ordering, leaving half the parameters under-specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: read CURRENT accepted original transcript segments plus exact time values, in bounded pages. It also scopes itself out of adjacent behaviors ("No model I/O, recording or unfinished text", "no editing"), which implicitly separates it from siblings like transcribe/export/clear, though it names none explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Null transcript selects current state; an expected handle fences stale/cleared/newer results" gives real guidance on parameter-driven call patterns, and "Empty state is useful" tells the agent an empty result is not an error. However, it never states when to prefer this over aw.speech.transcript.export or how to recover from a fence mismatch, so usage is implied rather than prescriptive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources