Skip to main content
Glama

mcp-server

by ar.com.muovi
OverviewDiscussionsAdmin

Create task draft

muovi_create_task_draft

Save a task draft on Muovi for the person you are helping, and get back a link for them. The person opens the link, reviews the draft, signs in to Muovi and publishes it themselves. This tool publishes nothing and does not notify any professional. To hand over the full request, call muovi_get_service_requirements for the service first, ask the person every required question, and send the answers in slots (keyed by slot key) with location. If a required answer is missing, the result has status: "incomplete", lists the questions still to ask and carries no link: ask them and call again with every slot. If a value is not accepted, the result has status: "invalid_slots" and names each slot. A draft with every required answer opens on a review form with those answers filled in, without asking them again unless Muovi's own check of the request raises a question, and the person confirms the address on a map before publishing. Sending only description still saves a draft, and that link opens Muovi's assistant, which asks the person its questions. To direct the draft to one professional, pass professional_id, the id of any result from muovi_search_professionals: when the person publishes it, the task goes to that professional first for 24 hours and then opens to everyone, unless open_to_others is true, in which case it opens to everyone right away and that professional is still told. Set open_to_others from what the person chose; they can change it on the review form. A ProSite slug in professional_slug is still accepted instead of professional_id. Leave both out for a general request to get offers from several professionals. service_slug comes from muovi_list_services. A link nobody has opened expires 24 hours after it is created. The first person to open it takes the draft, signed in or not, and can reopen the link for up to 7 days, so give it only to that person. Do not include phone numbers, email addresses or other contact details in any text.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slotsNoOptional. The person's answers, keyed by slot key from `muovi_get_service_requirements`. Send each value in the slot's `value_format`.
titleNoOptional. A short title for the task, 5 to 80 characters. Left out, Muovi takes it from the description.
locationNoOptional. Where the job is: `neighborhood_slug`, `address`, or both. The address is saved as text; the person confirms the place on the map on Muovi.
zone_textNoOptional. Where the job is, as free text (neighborhood or area), up to 120 characters.
descriptionYesWhat the person needs done, in their words: 20 to 2000 characters.
service_slugYesThe service slug (from `muovi_list_services`), e.g. "electricidad".
budget_amountNoOptional. The person's budget in ARS, as a positive number.
open_to_othersNoOptional, with professional_id. True when the person also wants offers from other professionals right away; false or omitted gives the chosen professional the first 24 hours.
preferred_dateNoRequired with preferred_time "specific_date", otherwise omitted. YYYY-MM-DD, from today up to 90 days ahead (Argentina time).
preferred_timeNoOptional. When the person wants it done. Use "specific_date" together with `preferred_date`.
professional_idNoOptional. The `id` of a professional from `muovi_search_professionals` to direct the draft to. Omit for a general request.
time_preferencesNoOptional. The parts of the day that suit the person.
professional_slugNoOptional. A ProSite slug from an older link, instead of professional_id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover safety hints (`readOnlyHint=false`, `destructiveHint=false`, `openWorldHint=true`), but the description adds substantial behavioral context beyond them: return statuses (`incomplete`, `invalid_slots`), link expiry after 24 hours unopened and 7-day reopen window, first-opener ownership, professional routing (24-hour head start unless `open_to_others` is true), and a privacy constraint. This is rich, non-contradictory disclosure.

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

Conciseness5/5

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

Although long, the description is front-loaded with purpose and each sentence conveys a distinct behavioral rule, edge case, or workflow step. There is no filler or repetition; dense but necessary detail for a 13-parameter tool. Information is arranged logically from draft creation through routing, expiry, and privacy.

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?

With no output schema, the description carries the return-value burden and does so by naming the `incomplete` and `invalid_slots` statuses and explaining the link returned on success. It also covers prerequisites, routing behavior, link lifecycle, and privacy rules. Given the tool's complexity and annotation coverage, an agent has enough context to invoke it 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 100%, so the baseline is 3. The description goes beyond the schema by explaining the process behind `slots` (keyed by slot key from `muovi_get_service_requirements`, missing answers produce `status: incomplete`), the practical meaning of `professional_id` and `open_to_others` (24-hour exclusivity versus immediate opening), and the fallback to `professional_slug`. Some fields such as `title`, `budget_amount`, and `zone_text` add little beyond their schema descriptions, so it does not reach a full 5.

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?

The description opens with a specific verb and resource: 'Save a task draft on Muovi' and 'get back a link.' It immediately distinguishes this tool from publishing ('This tool publishes nothing and does not notify any professional') and from the full-request workflow that requires calling `muovi_get_service_requirements` first. An agent can identify the tool's role without opening the schema.

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?

It gives explicit when-to-use guidance: call `muovi_get_service_requirements` first, ask every required question, send answers in `slots` with `location`; use `professional_id` to direct the draft; omit both `professional_id` and `professional_slug` for a general request. It also states when `description` alone is sufficient. Alternatives and conditions are named rather than left to inference.

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

All mcp-server toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources