Skip to main content
Glama
Hermoso

Hermoso

Official

Import a channel’s past posts

backfill_posts
Idempotent

Import past channel posts into the performance record so hook analysis can use historical data; dry-run by default and resume with a cursor.

Instructions

Import this brand's PAST posts from a channel into the performance record, so 'which hook works' can draw on history rather than only on what was published since Hermoso started recording. Supports facebook, instagram, threads, youtube, tiktok, pinterest and bluesky; the others say plainly why they cannot (LinkedIn has no enumerate-my-posts endpoint on our grant, X bills per read so it is excluded from bulk import, Google Business has had no per-post insights since 2023, and Telegram's Bot API cannot read a chat's past messages at all — nothing published before Hermoso is recoverable through a bot token). BOUNDED, RESUMABLE AND QUOTED: it runs as a DRY RUN by default and tells you how many posts it found and what reading them will cost — pass confirm:true to import, and pass the returned cursor to continue. AN IMPORTED POST IS WEAKER EVIDENCE THAN A RECORDED ONE and is labelled 'backfilled': its hook is recovered ONLY where the post matches a Hermoso creation by asset or caption. A post made outside Hermoso stays UNATTRIBUTED — it counts toward channel and format totals but never votes on which hook works. Never guess a hook from a caption. Free.

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": {
      "channel": "<channel>"
    },
    "name": "backfill_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNohow many posts this page (default 50, max 200)
cursorNoresume from a previous run
channelYeswhich channel to import from
confirmNoactually import — omit for a dry run that only quotes the cost
accountRefNowhich Page / account, when the profile has more than one

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.374
    • changedInput schema / properties / accountRef / description
      Previous value: -"which Page / account, when the brand has more than one"New value: +"which Page / account, when the profile has more than one"
  2. Addedv0.1.161

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint false, idempotent, openWorld, non-destructive), the description discloses the DRY-RUN default, that a cost quote is returned, that runs are bounded and resumable via a cursor, and that the operation is free. It also explains the downstream data-model consequence — imported posts are labelled 'backfilled', weaker evidence, and stay UNATTRIBUTED unless matched by asset or caption. That is exactly the behavioral context annotations cannot carry.

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 purpose and a bolded 'BOUNDED, RESUMABLE AND QUOTED' section, then caveats. Dense rather than padded, though the long parenthetical cataloguing LinkedIn, X, Google and Telegram costs some length for information that only matters if an agent tries an unsupported channel.

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 mutation tool with no output schema, the description covers the essentials an agent needs to call it safely: default safe mode, the confirm gate, pagination/resume path, which channels work, and what the imported data means downstream. Remaining details (return shape beyond counts and cost) are adequately implied by the quote step.

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, but the description adds real meaning on top: confirm:true is the switch from quote to import, and the cursor is described as coming back from a prior run and being passed in to continue — a usage pattern the schema only hints at. The limit and accountRef parameters are left entirely to 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 and resource — importing a brand's past posts from a named channel into the performance record — and frames the outcome ('so which hook works can draw on history'). It implicitly contrasts with recorded posts but never names a sibling tool such as list_published_posts, so differentiation is by concept rather than by routing.

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?

When-to-use is clear (to give hook analysis historical depth) and when-not is unusually thorough: each unsupported channel is listed with the concrete reason (LinkedIn grant, X per-read billing, Google Business insights discontinued, Telegram Bot API limits). It also states the dry-run default and confirm:true to actually import. What's missing is explicit direction to an alternative tool for viewing already-recorded posts.

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