Skip to main content
Glama
hermoso-ai

Hermoso

Official

Publish to LinkedIn

post_to_linkedin
Destructive

Publish text and an optional image to a connected personal LinkedIn profile; images must be Hermoso-hosted and require explicit approval before public posting.

Instructions

Use this when the user wants to post to their personal LinkedIn profile. Publishing costs no credits. Publish a post to the user’s connected LinkedIn profile — text, and optionally an image (pass its served URL as imageUrl). The image does NOT have to be something Hermoso generated: LinkedIn is served the bytes from us, so the URL must be Hermoso-hosted, and upload_file turns ANY file the user already has into exactly that. This PUBLISHES immediately and PUBLICLY — ALWAYS show the user the exact text and get an explicit yes BEFORE calling. Needs a connected LinkedIn account (Settings > Connectors > LinkedIn).

Input Schema

NameRequiredDescriptionDefault
hookNoWHAT ANGLE this post is built on, recorded only at publish time. post_performance ranks hooks on it (a winner needs 5 posts sharing ONE hook), so pass a list_hooks id (e.g. "direct_callout", "before_after") or reuse your own wording EXACTLY across a campaign. Omit it and this post never votes on which hook works.
textYesthe post text
brandNoWHICH PROFILE this post belongs to — id or exact name from list_brands (a shared workspace: its profile id). Beats the connection's pin for THIS CALL ONLY; a name that matches no profile, or two, is REFUSED and nothing is posted.
ideaIdNoshort id of the content-plan idea this post came from
recipeNothe post's FORMAT id, e.g. "slideshow" or "imessage_chat" — post_performance groups by it, so reuse one id per format
subjectNoWHAT THIS POST IS ABOUT — product, feature, offer or theme (e.g. "winter coat", "free trial"). post_performance's second grouping axis: reuse the exact wording, as with hook.
imageUrlNoa Hermoso-hosted image URL to attach (≤12MB) — a Hermoso render, or ANY file of the user’s own put through upload_file first. An arbitrary external host is refused (we fetch the bytes ourselves).
imageUrlsNoA CAROUSEL IS NOT AVAILABLE ON A PERSONAL PROFILE — LinkedIn's organic multi-image post publishes from a COMPANY PAGE. Passing several here is refused by name rather than posting slide 1; use post_to_linkedin_page instead.
visibilityNodefault PUBLIC
allowDuplicateNopost it even though an identical post was just made or attempted. Only pass this when the user genuinely wants the same thing posted twice, or when you have LOOKED at the account and confirmed a timed-out attempt did not land.
idempotencyKeyNoSAFE RETRIES — any stable string: a repeat of the SAME publish within 24h returns the ORIGINAL post id instead of posting again (an identical publish is also auto-recognised for 10 minutes). On a timeout or an ambiguous error, CALL AGAIN WITH THE SAME KEY: it reports the original post or publishes it once. It never posts twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.374
    • changedInput schema / properties / brand / description
      Previous value: -"WHICH BRAND this post belongs to — id or exact name from list_brands (a shared workspace: its profile id). Beats the connection's pin for THIS CALL ONLY; a name that matches no brand, or two, is REFUSED and nothing is posted."New value: +"WHICH PROFILE this post belongs to — id or exact name from list_brands (a shared workspace: its profile id). Beats the connection's pin for THIS CALL ONLY; a name that matches no profile, or two, is REFUSED and nothing is posted."
  2. Changed4 schema fields changedv0.1.320
    • changedInput schema / properties / brand / description
      Previous value: -"WHICH BRAND this post belongs to — the id or exact name from list_brands (a workspace shared with you: its profile id). Use it whenever the account has more than one brand and you are not certain which one this connection is pinned to: it beats the pin for THIS CALL ONLY and changes nothing about the connection. A name that matches no brand, or two brands, is REFUSED and nothing is posted — never resolved to the pin, which is the account you were guarding against."New value: +"WHICH BRAND this post belongs to — id or exact name from list_brands (a shared workspace: its profile id). Beats the connection's pin for THIS CALL ONLY; a name that matches no brand, or two, is REFUSED and nothing is posted."
    • changedInput schema / properties / hook / description
      Previous value: -"WHAT ANGLE THIS POST IS BUILT ON — the single most valuable field here, and the only moment it can ever be recorded. post_performance groups on it to answer \"which hooks work\", and it needs 5 posts sharing ONE hook before it will call anything a winner, so REUSE THE SAME WORDING across a campaign instead of rephrasing it every time. Best of all, pass a hook id from list_hooks (e.g. \"direct_callout\", \"mid_problem\", \"before_after\") — those fold onto a stable key however they are spelled, so a whole brand accumulates evidence on one row. Your own wording is fine too; it just only groups when you repeat it exactly. Omitting it means this post can never vote on which hook works."New value: +"WHAT ANGLE this post is built on, recorded only at publish time. post_performance ranks hooks on it (a winner needs 5 posts sharing ONE hook), so pass a list_hooks id (e.g. \"direct_callout\", \"before_after\") or reuse your own wording EXACTLY across a campaign. Omit it and this post never votes on which hook works."
    • changedInput schema / properties / idempotencyKey / description
      Previous value: -"SAFE RETRIES. Publishing can take minutes (a video upload, a carousel of ten slides) and a transport can time out while the post SUCCEEDS — retrying blind is how the same thing gets posted twice. Pass any stable string here and a repeat of the SAME publish returns the ORIGINAL post id instead of posting again (24h). You do not have to: an identical publish is auto-recognised for 10 minutes anyway. If a call times out or errors ambiguously, CALL AGAIN WITH THE SAME KEY — that is the safe move, and it will either report the original post or publish it for the first time. It never posts twice."New value: +"SAFE RETRIES — any stable string: a repeat of the SAME publish within 24h returns the ORIGINAL post id instead of posting again (an identical publish is also auto-recognised for 10 minutes). On a timeout or an ambiguous error, CALL AGAIN WITH THE SAME KEY: it reports the original post or publishes it once. It never posts twice."
    • changedInput schema / properties / subject / description
      Previous value: -"WHAT THIS POST IS ABOUT — the product, feature, offer or theme (e.g. \"winter coat\", \"free trial\", \"founder story\"). The second grouping axis in post_performance. Same rule as hook: reuse the exact wording so posts about one subject land in one group."New value: +"WHAT THIS POST IS ABOUT — product, feature, offer or theme (e.g. \"winter coat\", \"free trial\"). post_performance's second grouping axis: reuse the exact wording, as with hook."
  3. Changed2 schema fields changedv0.1.281
    • addedInput schema / properties / ideaId
      Added value: +{
      +  "description": "short id of the content-plan idea this post came from",
      +  "type": "string"
      +}
    • addedInput schema / properties / recipe
      Added value: +{
      +  "description": "the post's FORMAT id, e.g. \"slideshow\" or \"imessage_chat\" — post_performance groups by it, so reuse one id per format",
      +  "type": "string"
      +}
  4. Changed1 schema field changedv0.1.251
    • addedInput schema / properties / brand
      Added value: +{
      +  "description": "WHICH BRAND this post belongs to — the id or exact name from list_brands (a workspace shared with you: its profile id). Use it whenever the account has more than one brand and you are not certain which one this connection is pinned to: it beats the pin for THIS CALL ONLY and changes nothing about the connection. A name that matches no brand, or two brands, is REFUSED and nothing is posted — never resolved to the pin, which is the account you were guarding against.",
      +  "type": "string"
      +}
  5. Addedv0.1.161

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety bar is lowered, yet the description still adds real context: the post goes out 'immediately and PUBLICLY', requires an explicit user confirmation of the exact text first, and needs a connected account. It does not surface the retry/idempotency behavior that lives in the schema, which keeps it from a 5.

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 trigger and the action, then prerequisites and the confirmation rule. Slightly long with overlapping sentences about image hosting, but no sentence is filler.

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?

For a destructive, publicly visible publish with no output schema, the description covers the trigger, account prerequisite, cost, media constraint, and the mandatory pre-publish confirmation. The only gap is that it says nothing about the returned post id or failure/retry handling, which the schema partially covers via idempotencyKey.

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% across 11 parameters, so structured fields already carry the semantics. The description only restates the text/imageUrl pairing and the Hermoso-hosted URL constraint, which the schema states more thoroughly; baseline 3 applies.

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 specific verb and resource ('Publish a post to the user's connected LinkedIn profile') and scopes it to the personal profile, which implicitly distinguishes it from the sibling post_to_linkedin_page (a company-page tool). An agent can tell what this does 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('Use this when the user wants to post to their personal LinkedIn profile'), a prerequisite (connected LinkedIn account via Settings > Connectors), and a cost note (no credits). It stops short of naming post_to_linkedin_page as the alternative for company pages, so the routing rule for that sibling is left to the schema.

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