delete_mediaDelete a media file by ID. Removes the file from storage and detaches it from any posts. Use this when the user wants to delete a media file.
| Name | Required | Description | Default |
|---|---|---|---|
| mediaId | Yes | The media file ID to delete. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark destructiveHint, so the bar is lower. The description adds useful behavioral detail by specifying that it removes the file from storage and detaches it from any posts, going beyond the annotation flags.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded, with each sentence contributing: the operation, the concrete effect, and the usage context. There is minor redundancy in repeating 'delete a media file,' but no wasted content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter delete operation, the description plus annotations fully cover what an agent needs: what it does, what it affects, when to use it, and that it is destructive. An output schema is not necessary for this operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and mediaId is fully documented in the schema. The description adds no additional parameter meaning, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Delete a media file by ID') plus concrete effects ('Removes... detaches...'). This clearly distinguishes it from sibling delete tools for posts, labels, schedules, and other resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this when the user wants to delete a media file.' This gives clear usage context, though it does not name exclusions or alternatives, which is acceptable given the resource is distinct.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools occupy adjacent spaces, especially the interactive view_* tools versus their get_/list_ counterparts (view_posts/list_posts, view_analytics/get_analytics) and the multiple upload paths (upload_media, create_media_upload, multipart flow). Detailed 'Use this when' guidance helps, but an agent could still misselect between compose_post and create_post or between bulk_posts and the individual delete/retry/update operations.
Tool names follow a highly consistent verb_noun pattern throughout: create/get/update/delete/list for each resource (posts, media, labels, channel sets, RSS feeds, schedules), plus publish/approve/reject/retry/upload/view. No style mixing or inconsistent casing.
51 tools is an extremely large surface, crossing the calibration's 50+ extreme threshold. While the platform covers many subdomains, this volume is likely to overwhelm agents and makes the toolkit unwieldy for an MCP server.
The toolkit provides broad lifecycle coverage: CRUD for posts, media, labels, channel sets, RSS feeds, and schedules, plus publishing, approvals, retries, bulk operations, analytics, quota, channel health, and media upload variants. Minor gaps exist, such as no get_channel single-resource getter and no way to update media labels directly, but agents can work around these.