Skip to main content
Glama

Change a call request

revise_task
Destructive

Change a task’s request or recipient, using the version from its latest reply. This can settle the earlier preparation and start new preparation, which can be charged within the saved limits. A task that has changed or been approved may refuse the edit. Returns the task at its new step.

Input Schema

NameRequiredDescriptionDefault
briefNoWhat you know that the call needs, one point per field, up to 300 characters each. Request and brief together fit 2,000 characters.
taskIdYesThe task’s id: task.taskId in any reply about it, or from prepare_task, list_tasks or find_task.
requestYesWhat the owner wants, in their words, with every name, number, reference and preference they gave. Before preparing, ask the owner in one message for what’s missing: each fact saves JooVoice a question. JooVoice decides the call’s language, accent and voice, so you don’t have to; a fact about the other side still counts, e.g. “she only speaks Italian”. For example, a table needs the day, time, how many, the name it’s under and what else would do (ask them; don’t assume flexibility); an appointment, the service, who should do it and whether anyone else is fine, when they’re free and their name; a refund or bill, the order or account number, the name on it, what went wrong, the amount and what they’d accept.
versionYesThe task’s version from the latest reply (task.version or next[].arguments), exactly as given.
timezoneYesThe owner’s IANA time zone, e.g. Asia/Singapore.
direct_callNoSet true to ring the owner’s own phone directly, with no Start link. Only their current verified account number can be called this way; any other number fails. With destinations [], JooVoice uses that number. Preparing still doesn’t dial: you call approve_call. Normally ask whether they’re ready first; an explicit instruction, an agreed routine or urgency can justify going ahead without another reply.
destinationsYesWho to call: one number with its country code, e.g. +6591234567, or [] to let JooVoice find the business from the request.
destinationTimezonesNoThe IANA time zone of a number you supplied, keyed by that number, when you know it, e.g. {"+14155550100":"America/Los_Angeles"}. Never put the owner’s time zone here.

Output Schema

NameRequiredDescriptionDefault
hintNoOptional guidance for helping the owner at this step. Advisory; never a permission grant. Wording may change.
nextYesCalls to make next.
statusYespending: check again later; requires_user_action: the owner must act; error: refused.
meaningYesWhat happened, for you.
sayToOwnerYesA line for the owner.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / direct_call
      Added value: +{
      +  "description": "Set true to ring the owner’s own phone directly, with no Start link. Only their current verified account number can be called this way; any other number fails. With destinations [], JooVoice uses that number. Preparing still doesn’t dial: you call approve_call. Normally ask whether they’re ready first; an explicit instruction, an agreed routine or urgency can justify going ahead without another reply.",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

The description adds meaningful behavior beyond the annotations: revising can settle earlier preparation and start new preparation, may incur charges within saved limits, may be refused for changed or approved tasks, and returns the task at its new step. The destructiveHint annotation already signals mutation risk, so this is useful supplemental context rather than a contradiction.

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?

The description is three compact sentences, front-loads the tool’s purpose, then adds behavioral caveats and return behavior. It is appropriately sized, with only minor vagueness around charging and saved limits.

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

Completeness4/5

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

Given the rich input schema and the presence of an output schema, the description covers the main operational context an agent needs: use the latest version, changing can trigger new preparation and charges, edits may be refused, and it returns the task at its new step. It could be stronger with explicit sibling routing, but it is otherwise complete.

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 100%, so the schema already documents all parameters in detail. The description reinforces that the request/recipient are being changed and that the version comes from the latest reply, but it adds little parameter-level meaning beyond the schema.

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 description states a specific verb-resource pair: change a task’s request or recipient. It also clarifies that the edit uses the task’s latest reply version, which distinguishes it from creating a new task, though it does not explicitly name prepare_task or other siblings.

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?

Usage is implied by the prerequisite to use the version from the latest reply and by the warning that changed or approved tasks may refuse the edit. However, it does not explicitly say when to use this instead of prepare_task, approve_call, or other task 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