Skip to main content
Glama

aw.speech.transcribe

Original Tiny/Base whole-file transcription with a CURRENT shared transcript. Explicit SAME-session original encoder handle required; Run at most64 original decoder steps for Tiny or32 for Base per explicit call, with identical source/model/language/output and the CURRENT handle returned by this same tool. Use a NEW operationId only when advancing; after a failed call reconcile jobs and the last accepted receipt before deciding whether to explicitly resubmit the exact same UUID and inputs. Never swap in the file-only decoder continuation. Pending is NOT text. On original completion atomically retain validated original segments in this session encrypted vault and return a whole TXT/SRT plus transcript handle. Read segments or export BOTH original formats without another inference; Clear is separate. Old whisper file tools unchanged. Same30s/TTL/storage/jobs/admission/quotas, no truncation, automatic heavy retry, device/OS recognition, E2EE/backup erasure/all139/capacity/accuracy claim.

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>",
      "operationId": "<operationId>",
      "source": "<source>",
      "prepared": "<prepared>"
    },
    "name": "aw.speech.transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoonnx-community/whisper-tiny
outputNotxt
sourceYesAn immutable input or result handle belonging to this session; never a URL/path/base64.
sessionYesPrivate short-lived session capability returned by aw.session.open. Never publish or log it.
languageNoauto
preparedYes
operationIdYes
continuationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare readOnly=false, destructive=false and closed-world, but the description adds substantial context: atomic vault retention of validated segments on completion, a whole TXT/SRT plus transcript handle returned, TTL/storage/quota behavior, no truncation, and automatic heavy retry. It also clarifies that a pending status is not text, which prevents a common misread. Points are lost because the final sentence (device/OS recognition, E2EE/backup erasure/all139/capacity/accuracy claim) is unparseable boilerplate that conveys no actionable behavior.

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

Conciseness2/5

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

The text is a run-on chain of all-caps fragments with missing spaces ("at most64", "for32", "Same30s/TTL/"), and key rules are not front-loaded or grouped. The trailing sentence is a comma-spliced list of unrelated claims that no agent can act on. Density here is compression, not conciseness.

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?

For an 8-parameter, non-read-only tool with no output schema and only 25% schema coverage, the description does cover return values, atomicity, idempotency on retry, and storage lifetime. However the failure/retry loop is described only telegraphically and the closing claims about quotas, E2EE erasure, and 'accuracy claim' are left undefined, so an agent cannot fully model error handling or limits.

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

Parameters4/5

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

Schema coverage is only 25%, so the description has to carry weight, and it does for several parameters: model choice is tied to a 64-step (Tiny) or 32-step (Base) budget, operationId reuse vs. a new value when advancing is spelled out, continuation is explicitly the wrong handle to pass, and output is constrained to whole TXT/SRT. Source/prepared/language semantics are only glancingly covered (the same-session handle requirement is asserted but not explained), leaving gaps at low schema coverage.

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?

The opening states a specific verb and resource: whole-file transcription with the Tiny/Base models, producing a shared transcript. It also distinguishes itself from the file-only decoder path ("Never swap in the file-only decoder continuation" and "Old whisper file tools unchanged"). The signal is real but buried under undefined jargon ("Original", "CURRENT", "receipt"), so an agent must work to extract it.

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

Usage Guidelines4/5

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

It gives concrete when-to guidance: use a new operationId only when advancing, reconcile jobs and the last accepted receipt after a failure before resubmitting the same UUID, and read segments or export formats without another inference (routing to the read/export siblings). It also states an explicit exclusion about the file-only decoder. What is missing is a plain statement of when to pick this tool over the encode/decode step tools.

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