Skip to main content
Glama

Ask Reedapt for a change

ask_reedapt

Hands Reedapt a request about a finished dub in plain words, such as "Is line 3 natural?" or "Make the greeting warmer". Early access: accounts that don't have it yet get NOT_AVAILABLE.

Instructions

Hands Reedapt a request about a finished dub in plain words, such as "Is line 3 natural?" or "Make the greeting warmer". Early access: accounts that don't have it yet get NOT_AVAILABLE. With autonomy "ask" (the default) Reedapt answers, or proposes a change and waits: the returned run has status needs_input, a proposal and options. Show the person the proposal and call answer_run with their choice. With "decide" Reedapt applies changes itself, so use it only when the person said to. Each request counts against the plan's allowance.

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": {
      "dub_id": "<dub_id>",
      "request": "<request>"
    },
    "name": "ask_reedapt"
  }
}

Input Schema

NameRequiredDescriptionDefault
dub_idYesThe dub's id, such as dub_…
requestYesThe request, in plain words. Say which lines (by number) when you can.
autonomyNoask

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true); the description adds substantially more — the NOT_AVAILABLE error for accounts without early access, the returned run shape (status needs_input, `proposal`, `options`), the fact that 'decide' mutates the dub directly, and that each call consumes plan allowance.

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

Conciseness4/5

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

Front-loaded with the purpose and examples, and no sentence is filler — the availability caveat, mode semantics, and quota note all matter. It is a single dense paragraph mixing several concerns, so scanning for the autonomy rules takes a second pass.

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

Completeness5/5

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

There is no output schema, and the description compensates by describing exactly what the returned run looks like in 'ask' mode and what the agent must do next. Combined with the quota and availability warnings, an agent has everything needed to call and handle this tool correctly.

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 67%, so the two string params are self-documented, but the description adds real meaning for `autonomy` by explaining what each enum value does and which is default. It does not add anything for `dub_id` beyond the schema, leaving one small gap.

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

Purpose5/5

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

States a specific verb and resource ('Hands Reedapt a request about a finished dub') and grounds it with two concrete example requests. It is clearly distinguishable from answer_run (which consumes the proposal) and from edit_lines (deterministic editing).

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

Usage Guidelines5/5

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

Explicitly contrasts the two autonomy modes: 'ask' is the default and returns a proposal, 'decide' applies changes itself and should be used 'only when the person said to.' It also routes the agent to the correct follow-up ('call answer_run with their choice') and warns about the early-access NOT_AVAILABLE path.

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