Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Run autopilot now / approve its drafts

run_post_refill
Destructive

Preview, approve, edit, or discard social autoposting drafts, or run the daily post batch now instead of waiting for its scheduled turn.

Instructions

Run AUTOPILOT POSTING (autoposting) NOW instead of waiting for its daily turn, or REVIEW the drafts it made — "approve them all", "delete that one", "change the caption", "too salesy, remember that". PREVIEW BY DEFAULT: it returns the posts it WOULD make — each new picture’s scene, the caption, the channels and the price — rendering nothing and queueing nothing. The preview still WRITES the scenes and copy with a model, which bills a few credits (the reply says how many). dryRun:false actually renders a fresh image or video for each post within the budget (credits are spent) and then, by mode, schedules them ("auto") or keeps them as drafts ("review"). It never re-posts the Library. REVIEWING A BATCH: pass approve (draft ids, or ["all"]) to schedule drafts, discard to delete them, edit ([{id, message?, captions?, title?, at?, channels?}]) to change one first (a new at reschedules it); get_post_refill lists them. learn saves notes future batches follow (free). redo remakes ONE draft from a note: PAID, so without confirm:true it returns only the price; confirm only on the user’s yes. A scheduled post can still be pulled before it goes out with cancel_scheduled. Every caption is screened against the voice rules and a failing one is dropped, so a plan can come back shorter than the cadence — the reason is in the notes.

Input Schema

NameRequiredDescriptionDefault
editNoREVIEW: change drafts before approving them. Edited copy is screened by the voice rules.
redoNo
forceNoplan a preview even while autoposting is switched off — useful for showing someone what it would do before they turn it on.
learnNonotes for future batches, e.g. "too salesy". Free.
dryRunNodefault TRUE (a preview: nothing rendered, nothing queued; the copy it writes bills a few credits). false renders fresh creative and schedules or drafts it per the mode.
approveNoREVIEW: draft ids to schedule, or ["all"]. A draft whose time has passed moves to the next free posting slot.
discardNoREVIEW: draft ids to delete, or ["all"]. Nothing is posted for them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.1.398
    • addedInput schema / properties / approve
      Added value: +{
+  "description": "REVIEW: draft ids to schedule, or [\"all\"]. A draft whose time has passed moves to the next free posting slot.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / discard
      Added value: +{
+  "description": "REVIEW: draft ids to delete, or [\"all\"]. Nothing is posted for them.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / dryRun / description
      Previous value: -"default TRUE (preview only). false actually queues the posts."New value: +"default TRUE (a preview: nothing rendered, nothing queued; the copy it writes bills a few credits). false renders fresh creative and schedules or drafts it per the mode."
    • addedInput schema / properties / edit
      Added value: +{
+  "description": "REVIEW: change drafts before approving them. Edited copy is screened by the voice rules.",
+  "items": {
+    "properties": {
+      "at": {
+        "description": "ISO time, at least 5 minutes ahead",
+        "type": "string"
+      },
+      "captions": {
+        "additionalProperties": {
+          "type": "string"
+        },
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "channels": {
+        "description": "narrow to some of the draft’s own channels",
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "id": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / force / description
      Previous value: -"plan even while the refill is switched off — useful for showing someone what it would do before they turn it on. Combined with dryRun:false it still respects a stored dryRun."New value: +"plan a preview even while autoposting is switched off — useful for showing someone what it would do before they turn it on."
    • addedInput schema / properties / learn
      Added value: +{
+  "description": "notes for future batches, e.g. \"too salesy\". Free.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / redo
      Added value: +{
+  "properties": {
+    "change": {
+      "description": "caption keeps the picture",
+      "enum": [
+        "both",
+        "caption",
+        "picture"
+      ],
+      "type": "string"
+    },
+    "confirm": {
+      "description": "omit for the price only",
+      "type": "boolean"
+    },
+    "feedback": {
+      "type": "string"
+    },
+    "id": {
+      "type": "string"
+    },
+    "remember": {
+      "description": "save the note too (default true)",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "id"
+  ],
+  "type": "object"
+}
  2. Addedv0.1.161

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (which only flag destructive/openWorld/non-idempotent). It discloses that preview is the default, that even a preview bills a few credits via the model, that dryRun:false actually spends credits to render, that redo is PAID and gated by confirm:true, that learn is free, and that captions failing voice rules are dropped — exactly the credit/auth/destruction context annotations cannot convey.

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 core action is front-loaded and the batch-review verbs are grouped logically. It is dense and somewhat long with repeated credit/draft phrasing, but nearly every clause carries operational information, so little is waste.

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 a 7-param, nested-object, no-output-schema tool, the description covers what comes back (scene, caption, channels, price, credit count), the default preview vs real render, scheduling/draft modes, and the caption-screening edge case — nothing an agent needs to call it correctly is missing.

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 86%, so the schema carries most param meaning. The description still adds value by explaining mode-dependent behavior of dryRun, the ["all"] shorthand for approve/discard, the paid vs free distinction between redo and learn, and that a new `at` reschedules a draft.

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 specific verbs and resources: run autoposting now, or review/approve/discard/edit its drafts. It explicitly distinguishes itself from siblings (get_post_refill lists drafts, cancel_scheduled pulls a scheduled post), so an agent can route correctly without opening other schemas.

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?

Explicit when-to-use (skip the daily turn, review a batch) plus named alternatives for adjacent needs (get_post_refill for listing, cancel_scheduled for pulling). It even says force is for previewing while autoposting is off, which is a precise conditional.

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

Deploy Server

Other Tools