Skip to main content
Glama

Editar textos de un borrador

update_draft_texts
DestructiveIdempotent

Cambia título, descripción y el texto propio de cada red (y el título de YouTube), youtube_tags SEO y first_comment de YouTube de un borrador que todavía no se mandó a publicar, incluidos videos subidos en PilotControl. Pide antes la publicación con get_post y pasa su version. scheduled_for cambia o quita solo la fecha prevista del borrador si el usuario lo pidió. No publica ni toca lo programado o publicado.

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": {
      "post_id": "<post_id>",
      "version": "<version>"
    },
    "name": "update_draft_texts"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNo
post_idYes
targetsNo
versionYesLa versión que devolvió get_post; evita pisar un cambio hecho desde PilotControl
descriptionNo
youtube_tagsNoEtiquetas SEO de YouTube, sin #, distintas de los hashtags; [] las quita
first_commentNoPrimer comentario de YouTube; vacío lo quita. No se envía al editar el borrador
scheduled_forNoNueva fecha futura pedida por el usuario, o null para quitar la fecha del borrador; no lo programa hasta publicar

Output Schema

NameRequiredDescriptionDefault
titleYes
formatYes
sourceYes
statusYes
post_idYes
targetsYes
versionYes
brand_idYes
editableYes
created_atYes
descriptionYes
youtube_tagsNo
first_commentNo
scheduled_forYes
writing_contextNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructive=true and idempotent=true, and the description adds real context beyond them: edits apply only to unpublished drafts, the version parameter prevents overwriting concurrent changes made in PilotControl, and nothing scheduled or published is altered. These are exactly the concurrency and blast-radius facts an agent needs before calling a destructive mutation.

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 primary action and field list, then the get_post/version prerequisite, then the scheduled_for caveat, then the safety boundary. The mid-sentence parenthetical '(y el título de YouTube)' interrupts the flow slightly, but no sentence is filler.

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?

For an 8-parameter destructive mutation with an output schema and annotations already present, the description supplies what those do not: draft-only scope, stale-write protection via version, conditional scheduling behavior, and the no-publish boundary. An agent has enough to invoke it correctly and safely.

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?

With 50% schema description coverage, the description compensates by mapping free-form field names to meaning: per-platform text vs. general description, YouTube-only title, SEO tags distinct from hashtags, first_comment, and the conditional purpose of scheduled_for (date preview only, not scheduling). post_id and version are only touched implicitly, so it is not quite complete.

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 concrete verb ('Cambia') plus the resource (texts of a draft not yet published) and enumerates the editable fields: title, description, per-platform caption/YouTube title, youtube_tags, first_comment, scheduled_for. The closing line 'No publica ni toca lo programado o publicado' explicitly separates it from publish_post/reschedule_post, so an agent can route correctly without opening schemas.

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?

Gives an explicit prerequisite workflow: 'Pide antes la publicación con get_post y pasa su version', and conditions scheduled_for on the user having asked for it. It also states the negative case (doesn't publish, doesn't touch scheduled/published), though it never names a sibling alternative for editing already-published content, which is the one gap.

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