Skip to main content
Glama
metricool

mcp-metricool

Official
by metricool

update_schedule_post

Modify scheduled posts in Metricool by updating content, date, or media. Confirm changes with the user and ensure compliance with platform-specific requirements like character limits or media types. No retries on errors.

Instructions

Update a scheduled post in Metricool. You need the id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. Ask the user if they're sure they want to modify the post, including what will be changed, and require them to confirm. Do not retry if there is a problem. To update the post, ensure the full original content is included in the request, modifying only the new information while keeping the rest unchanged and maintaining the original structure. If the post include Instagram, is a must to have at least one image or video. Posts must include an image or a carousel, Reels must include a video, and Stories can include either an image or a video. If you don't have more information, you can ask the user about it and wait until you have the information. If the post include Pinterest, is a must to have a image and the board where to publish the pin. If you don't have more information, you can ask the user about it and wait until you have the information. If the post include Youtube, is a must to have a video, select the audience (if it's video made for kids or not) and the title of the video. If you don't have more information, you can ask the user about it and wait until you have the information. If the post include Tiktok, is a must to have at least one image or video. If you don't have more information, you can ask the user about it and wait until you have the information. If the post is Facebook Reel, is a must to have a video. If is Facebook Story, image or video is needed. If you don't have more information, you can ask the user about it and wait until you have the information. If the post is Bluesky, make sure the text does not exceed 300 characters. If the content exceeds that limit, do not retry and return an error informing the user: "Error: The text exceeds the 300-character limit allowed on Bluesky. Please edit it." If the post is for X (formerly Twitter), make sure before posting that the text does not exceed 280 characters. You must NOT split the message into multiple tweets or threads, the message must be evaluated strictly against a 280-character limit. If the text exceeds 280 characters, do not retry and return only the following error message and stop processing:

The date can't be in the past.

Args: date: Date and time to publish the post. The format is YYYY-MM-DDT00:00:00 id: id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. blog id: Blog id of the Metricool brand account. info: Data of the post to be scheduled. Should be a json object with the following fields: id: id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. The format is "id": uuid: uuid of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. The format is "uuid":"" autoPublish: True or False, default is True. descendants: list with the args of the other posts if it is a thread with the format [args of the second post, args of the third post,... ], default is empty list if there is no thread. draft: True or False, default is False. firstCommentText: Text of the first comment of the post. Default "" hasNotReadNotes: True or False, default is False. media: default is empty list. mediaAltText: default is empty list. providers: always need at least one provider with the format [{"network":""}]. Use "twitter" for X posts. publicationDate: Date and timezone of the post. The format is {dateTime:"2025-01-01T00:00:00", timezone:"Europe/Madrid"} shortener: True or False, default is False. smartLinkData: default is {ids:[]} text: Text of the post. Always you need to add the networkData for the posts, as empty if you don't have more information. Only include the networkData for the networks you have in the providers list. The format is "twitterData": {"tags":[]}, Tags is used for tagging people on the images of the post, not hashtags. "facebookData": {"type":"", "title":"", "boost":, "boostPayer":"", "boostBeneficiary":""}, Facebook type can be "POST", "REEL" or "STORY" Facebook title is only available for Facebook videos (This is separate from the main text of the post). Facebook boost, boostPayer, and boostBeneficiary are only included if they are promoted posts. "instagramData": {"type": "" (default = POST), "collaborators":[{username: "string", deleted: false}]], "showReelOnFeed": "" (default = true), "boost":, "boostPayer":"", "boostBeneficiary":""}, Instagram type can be "POST", "REEL" or "STORY". "linkedinData": {"documentTitle": "", "publishImagesAsPDF": "" (default = false), "previewIncluded": "" (default = true), "type": "" (default = post), "poll": {"question": "", "options": [{"text": ""}, {"text": ""}], "settings": {"duration": ""}}}, Linkedin type can be "post" or "poll". If there is a documentTitle in Linkedin, publishImagesAsPDF must be true. Linkedin poll duration can be "ONE_DAY", "THREE_DAYS", "SEVEN_DAYS " or "FOURTEEN_DAYS ". "pinterestData": {"boardId":"", "pinTitle":"","pinLink":"", "pinNewFormat":""}, "youtubeData": {"title": "", "type": "" (default = video), "privacy": "" (default = public), "tags": [ "", "" ], "category": "" (optional field), "madeForKids": ""}, Youtube type can be "video" or "short" and privacy can be "public", "unlisted" or "private". Youtube category can be FILM_ANIMATION, AUTOS_VEHICLES, MUSIC, PETS_ANIMALS, SPORTS, TRAVEL_EVENTS, GAMING, PEOPLE_BLOGS, COMEDY, ENTERTAINMENT, NEWS_POLITICS, HOWTO_STYLE, EDUCATION, SCIENCE_TECHNOLOGY, NONPROFITS_ACTIVISM. "twitchData": {"autoPublish":"", "tags":[]}, "tiktokData": {"disableComment": "" (default = false), "disableDuet": "" (default = false), "disableStitch": "" (default = false), "privacyOption": "" (default = "PUBLIC_TO_EVERYONE"), "commercialContentThirdParty": "" (default = false), "commercialContentOwnBrand": "" (default = false), "title": "", "autoAddMusic": "" (default = false), "photoCoverIndex": "" (default = 0)}, Tiktok privacyOption can be "PUBLIC_TO_EVERYONE", "MUTUAL_FOLLOW_FRIENDS", "FOLLOWER_OF_CREATOR" or "SELF_ONLY". "blueskyData": {"postLanguages":["",""]}, "threadsData":{"allowedCountryCodes:["",""]}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
blog_idYes
dateYes
idYes
infoYes

Implementation Reference

  • The handler function decorated with @mcp.tool() registers and implements the 'update_schedule_post' tool. It performs a PUT request to the Metricool API to update a scheduled post based on the provided id, date, blog_id, and info JSON.
    @mcp.tool()
    async def update_schedule_post(id: str, date:str, blog_id: int, info: json) -> str | dict[str, Any]:
        """
        Update a scheduled post in Metricool. You need the id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation.
        Ask the user if they're sure they want to modify the post, including what will be changed, and require them to confirm.
        Do not retry if there is a problem.
        To update the post, ensure the full original content is included in the request, modifying only the new information while keeping the rest unchanged and maintaining the original structure.
        If the post include Instagram, is a must to have at least one image or video. Posts must include an image or a carousel, Reels must include a video, and Stories can include either an image or a video. If you don't have more information, you can ask the user about it and wait until you have the information.
        If the post include Pinterest, is a must to have a image and the board where to publish the pin. If you don't have more information, you can ask the user about it and wait until you have the information.
        If the post include Youtube, is a must to have a video, select the audience (if it's video made for kids or not) and the title of the video. If you don't have more information, you can ask the user about it and wait until you have the information.
        If the post include Tiktok, is a must to have at least one image or video. If you don't have more information, you can ask the user about it and wait until you have the information.
        If the post is Facebook Reel, is a must to have a video. If is Facebook Story, image or video is needed. If you don't have more information, you can ask the user about it and wait until you have the information.
        If the post is Bluesky, make sure the text does not exceed 300 characters. If the content exceeds that limit, do not retry and return an error informing the user: "Error: The text exceeds the 300-character limit allowed on Bluesky. Please edit it."
        If the post is for X (formerly Twitter), make sure before posting that the text does not exceed 280 characters. You must NOT split the message into multiple tweets or threads, the message must be evaluated strictly against a 280-character limit. If the text exceeds 280 characters, do not retry and return only the following error message and stop processing:
    
        The date can't be in the past.
    
        Args:
         date: Date and time to publish the post. The format is YYYY-MM-DDT00:00:00
         id: id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation.
         blog id: Blog id of the Metricool brand account.
         info: Data of the post to be scheduled. Should be a json object with the following fields:
            id: id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. The format is "id":<integer>
            uuid: uuid of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. The format is "uuid":"<string>"
            autoPublish: True or False, default is True.
            descendants: list with the args of the other posts if it is a thread with the format [args of the second post, args of the third post,...  ], default is empty list if there is no thread.
            draft: True or False, default is False.
            firstCommentText: Text of the first comment of the post. Default ""
            hasNotReadNotes: True or False, default is False.
            media: default is empty list.
            mediaAltText: default is empty list.
            providers: always need at least one provider with the format [{"network":"<string>"}]. Use "twitter" for X posts.
            publicationDate: Date and timezone of the post. The format is {dateTime:"2025-01-01T00:00:00", timezone:"Europe/Madrid"}
            shortener: True or False, default is False.
            smartLinkData: default is {ids:[]}
            text: Text of the post.
            Always you need to add the networkData for the posts, as empty if you don't have more information. Only include the networkData for the networks you have in the providers list.
                The format is "twitterData": {"tags":[]}, Tags is used for tagging people on the images of the post, not hashtags.
                                "facebookData": {"type":"<string>", "title":"<string>", "boost":<double>, "boostPayer":"<string>", "boostBeneficiary":"<string>"},
                                    Facebook type can be "POST", "REEL" or "STORY"
                                    Facebook title is only available for Facebook videos (This is separate from the main text of the post).
                                    Facebook boost, boostPayer, and boostBeneficiary are only included if they are promoted posts.
                                "instagramData": {"type": "<string>" (default = POST), "collaborators":[{username: "string", deleted: false}]], "carouselTags":{"<number>":[{"username":"<string>","x":<double>,"y":<double>}]} (number is the index of the image within the carousel), "showReelOnFeed": "<boolean>" (default = true), "boost":<double>, "boostPayer":"<string>", "boostBeneficiary":"<string>"},
                                    Instagram type can be "POST", "REEL" or "STORY".
                                    There could be more than one collaborator, following the same structure.
                                    The carouselTags is a dictionary with the number of the image in the carousel as key and a list of tags for that image.
                                "linkedinData": {"documentTitle": "<string>", "publishImagesAsPDF": "<boolean>" (default = false), "previewIncluded": "<boolean>" (default = true), "type": "<string>" (default = post), "poll": {"question": "<string>", "options": [{"text": "<string>"}, {"text": "<string>"}], "settings": {"duration": "<string>"}}},
                                    Linkedin type can be "post" or "poll".
                                    If there is a documentTitle in Linkedin, publishImagesAsPDF must be true.
                                    Linkedin poll duration can be "ONE_DAY", "THREE_DAYS", "SEVEN_DAYS " or "FOURTEEN_DAYS ".
                                "pinterestData": {"boardId":"<string>", "pinTitle":"<string>","pinLink":"<string>", "pinNewFormat":"<boolean>"},
                                "youtubeData": {"title": "<string>", "type": "<string>" (default = video), "privacy": "<string>" (default = public), "tags": [ "<string>", "<string>" ], "category": "<string>" (optional field), "madeForKids": "<boolean>"},
                                    Youtube type can be "video" or "short" and privacy can be "public", "unlisted" or "private".
                                    Youtube category can be FILM_ANIMATION, AUTOS_VEHICLES, MUSIC, PETS_ANIMALS, SPORTS, TRAVEL_EVENTS, GAMING, PEOPLE_BLOGS, COMEDY, ENTERTAINMENT, NEWS_POLITICS, HOWTO_STYLE, EDUCATION, SCIENCE_TECHNOLOGY, NONPROFITS_ACTIVISM.
                                "twitchData": {"autoPublish":"<boolean>", "tags":[]},
                                "tiktokData": {"disableComment": "<boolean>" (default = false), "disableDuet": "<boolean>" (default = false), "disableStitch": "<boolean>" (default = false), "privacyOption": "<string>" (default = "PUBLIC_TO_EVERYONE"), "commercialContentThirdParty": "<boolean>" (default = false), "commercialContentOwnBrand": "<boolean>" (default = false), "title": "<string>", "autoAddMusic": "<boolean>" (default = false), "photoCoverIndex": "<integer>" (default = 0)},
                                    Tiktok privacyOption can be "PUBLIC_TO_EVERYONE", "MUTUAL_FOLLOW_FRIENDS", "FOLLOWER_OF_CREATOR" or "SELF_ONLY".
                                "blueskyData": {"postLanguages":["",""]},
                                "threadsData":{"allowedCountryCodes:["",""]}
        """
    
        url = f"{METRICOOL_BASE_URL}/v2/scheduler/posts/{id}?blogId={blog_id}&userId={METRICOOL_USER_ID}&integrationSource=MCP"
    
        response = await make_put_request(url, data=json.dumps(info))
    
        if not response:
            return ("Failed to update the post")
    
        return response
  • The @mcp.tool() decorator registers the update_schedule_post function as an MCP tool.
    @mcp.tool()
  • The docstring provides detailed schema for input parameters: id (str), date (str), blog_id (int), info (json) with structure for updating post data.
    """
    Update a scheduled post in Metricool. You need the id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation.
    Ask the user if they're sure they want to modify the post, including what will be changed, and require them to confirm.
    Do not retry if there is a problem.
    To update the post, ensure the full original content is included in the request, modifying only the new information while keeping the rest unchanged and maintaining the original structure.
    If the post include Instagram, is a must to have at least one image or video. Posts must include an image or a carousel, Reels must include a video, and Stories can include either an image or a video. If you don't have more information, you can ask the user about it and wait until you have the information.
    If the post include Pinterest, is a must to have a image and the board where to publish the pin. If you don't have more information, you can ask the user about it and wait until you have the information.
    If the post include Youtube, is a must to have a video, select the audience (if it's video made for kids or not) and the title of the video. If you don't have more information, you can ask the user about it and wait until you have the information.
    If the post include Tiktok, is a must to have at least one image or video. If you don't have more information, you can ask the user about it and wait until you have the information.
    If the post is Facebook Reel, is a must to have a video. If is Facebook Story, image or video is needed. If you don't have more information, you can ask the user about it and wait until you have the information.
    If the post is Bluesky, make sure the text does not exceed 300 characters. If the content exceeds that limit, do not retry and return an error informing the user: "Error: The text exceeds the 300-character limit allowed on Bluesky. Please edit it."
    If the post is for X (formerly Twitter), make sure before posting that the text does not exceed 280 characters. You must NOT split the message into multiple tweets or threads, the message must be evaluated strictly against a 280-character limit. If the text exceeds 280 characters, do not retry and return only the following error message and stop processing:
    
    The date can't be in the past.
    
    Args:
     date: Date and time to publish the post. The format is YYYY-MM-DDT00:00:00
     id: id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation.
     blog id: Blog id of the Metricool brand account.
     info: Data of the post to be scheduled. Should be a json object with the following fields:
        id: id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. The format is "id":<integer>
        uuid: uuid of the post to update. Get it from the get_scheduled_posts tool previous on the conversation. The format is "uuid":"<string>"
        autoPublish: True or False, default is True.
        descendants: list with the args of the other posts if it is a thread with the format [args of the second post, args of the third post,...  ], default is empty list if there is no thread.
        draft: True or False, default is False.
        firstCommentText: Text of the first comment of the post. Default ""
        hasNotReadNotes: True or False, default is False.
        media: default is empty list.
        mediaAltText: default is empty list.
        providers: always need at least one provider with the format [{"network":"<string>"}]. Use "twitter" for X posts.
        publicationDate: Date and timezone of the post. The format is {dateTime:"2025-01-01T00:00:00", timezone:"Europe/Madrid"}
        shortener: True or False, default is False.
        smartLinkData: default is {ids:[]}
        text: Text of the post.
        Always you need to add the networkData for the posts, as empty if you don't have more information. Only include the networkData for the networks you have in the providers list.
            The format is "twitterData": {"tags":[]}, Tags is used for tagging people on the images of the post, not hashtags.
                            "facebookData": {"type":"<string>", "title":"<string>", "boost":<double>, "boostPayer":"<string>", "boostBeneficiary":"<string>"},
                                Facebook type can be "POST", "REEL" or "STORY"
                                Facebook title is only available for Facebook videos (This is separate from the main text of the post).
                                Facebook boost, boostPayer, and boostBeneficiary are only included if they are promoted posts.
                            "instagramData": {"type": "<string>" (default = POST), "collaborators":[{username: "string", deleted: false}]], "carouselTags":{"<number>":[{"username":"<string>","x":<double>,"y":<double>}]} (number is the index of the image within the carousel), "showReelOnFeed": "<boolean>" (default = true), "boost":<double>, "boostPayer":"<string>", "boostBeneficiary":"<string>"},
                                Instagram type can be "POST", "REEL" or "STORY".
                                There could be more than one collaborator, following the same structure.
                                The carouselTags is a dictionary with the number of the image in the carousel as key and a list of tags for that image.
                            "linkedinData": {"documentTitle": "<string>", "publishImagesAsPDF": "<boolean>" (default = false), "previewIncluded": "<boolean>" (default = true), "type": "<string>" (default = post), "poll": {"question": "<string>", "options": [{"text": "<string>"}, {"text": "<string>"}], "settings": {"duration": "<string>"}}},
                                Linkedin type can be "post" or "poll".
                                If there is a documentTitle in Linkedin, publishImagesAsPDF must be true.
                                Linkedin poll duration can be "ONE_DAY", "THREE_DAYS", "SEVEN_DAYS " or "FOURTEEN_DAYS ".
                            "pinterestData": {"boardId":"<string>", "pinTitle":"<string>","pinLink":"<string>", "pinNewFormat":"<boolean>"},
                            "youtubeData": {"title": "<string>", "type": "<string>" (default = video), "privacy": "<string>" (default = public), "tags": [ "<string>", "<string>" ], "category": "<string>" (optional field), "madeForKids": "<boolean>"},
                                Youtube type can be "video" or "short" and privacy can be "public", "unlisted" or "private".
                                Youtube category can be FILM_ANIMATION, AUTOS_VEHICLES, MUSIC, PETS_ANIMALS, SPORTS, TRAVEL_EVENTS, GAMING, PEOPLE_BLOGS, COMEDY, ENTERTAINMENT, NEWS_POLITICS, HOWTO_STYLE, EDUCATION, SCIENCE_TECHNOLOGY, NONPROFITS_ACTIVISM.
                            "twitchData": {"autoPublish":"<boolean>", "tags":[]},
                            "tiktokData": {"disableComment": "<boolean>" (default = false), "disableDuet": "<boolean>" (default = false), "disableStitch": "<boolean>" (default = false), "privacyOption": "<string>" (default = "PUBLIC_TO_EVERYONE"), "commercialContentThirdParty": "<boolean>" (default = false), "commercialContentOwnBrand": "<boolean>" (default = false), "title": "<string>", "autoAddMusic": "<boolean>" (default = false), "photoCoverIndex": "<integer>" (default = 0)},
                                Tiktok privacyOption can be "PUBLIC_TO_EVERYONE", "MUTUAL_FOLLOW_FRIENDS", "FOLLOWER_OF_CREATOR" or "SELF_ONLY".
                            "blueskyData": {"postLanguages":["",""]},
                            "threadsData":{"allowedCountryCodes:["",""]}
    """
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes critical behaviors: the tool modifies existing posts (mutation), requires user confirmation before changes, has specific error handling (no retries, character limit errors), and includes platform-specific constraints (e.g., date can't be in the past, media requirements). However, it doesn't mention authentication needs or rate limits.

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

Conciseness2/5

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

The description is excessively long (over 800 words) and poorly structured. While it contains valuable information, it's not front-loaded—critical usage guidelines are buried among platform-specific details. The 'Args:' section duplicates information from earlier text, and the platform-specific rules could be summarized more efficiently. Every sentence adds value, but the overall presentation lacks conciseness.

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?

Given the tool's high complexity (mutation operation, 4 parameters with 0% schema coverage, no annotations, no output schema), the description provides exceptional completeness. It covers purpose, usage prerequisites, behavioral constraints, detailed parameter documentation, platform-specific requirements, error handling, and format specifications. For a tool with this complexity and no structured support, the description leaves no significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description must fully compensate. It provides extensive parameter semantics: explains that 'id' comes from 'get_scheduled_posts', details the 'date' format and constraint (can't be past), and comprehensively documents the complex 'info' JSON structure with all fields, formats, defaults, and platform-specific data requirements. This far exceeds the baseline expectation.

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 clearly states the tool's purpose: 'Update a scheduled post in Metricool.' It specifies the verb ('update'), resource ('scheduled post'), and platform ('Metricool'), distinguishing it from sibling tools like 'post_schedule_post' (create) and 'get_scheduled_posts' (read).

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?

The description provides explicit usage guidance: 'You need the id of the post to update. Get it from the get_scheduled_posts tool previous on the conversation.' It also includes detailed when-to-use rules for different social platforms (e.g., Instagram requires media, Bluesky has character limits) and explicitly states 'Do not retry if there is a problem.'

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

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/metricool/mcp-metricool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server