delete_mediaONLY an image no collection row and no project file references (bounded scan). Reclaims image quota from an abandoned build. Anything attached or holding content is refused (409) — relay the reason to the owner, never retry.
| Name | Required | Description | Default |
|---|---|---|---|
| mediaId | Yes | The media item ID (from list_media or upload_media) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the destructiveHint, the description discloses a concrete 409 refusal behavior when the media is attached or holding content, a bounded scan, and a clear operational rule (relay the reason to the owner, never retry). This materially changes how an agent should handle failures and is valuable beyond what annotations already say.
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 every clause earns its place, with the key precondition and failure behavior front-loaded. The phrasing is a bit telegraphic ('ONLY an image no collection row'), which slightly hurts readability, but there is no fluff.
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 one-parameter deletion tool with annotations and a fully documented schema, the description covers preconditions, quota effect, failure mode, and owner communication. The only minor gap is defining terms like 'collection row' and 'bounded scan' precisely for an agent without background context.
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?
The single parameter mediaId is already fully documented in the schema as coming from list_media or upload_media. The description reinforces that only image-type media should be targeted, but it does not need to add more because the schema coverage is 100%.
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?
The description identifies a specific action (reclaiming image quota) and a strict scope (only an image with no collection row or project file reference), which makes clear what delete_media does and when it applies. It is not as direct as 'deletes the specified media item' and does not explicitly distinguish itself from sibling deletion tools, but the bounded precondition separates it from broader deletions.
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?
Usage context is implied: it is the tool for reclaiming quota from abandoned builds where the media is only an image. It also gives an explicit when-not instruction (anything attached is refused with 409; never retry), but it does not name an alternative tool or state a comparison with siblings.
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.
Most tools are clearly separated by resource and action, and the descriptions are detailed enough to avoid most misselection. The main ambiguity is between deploy_files and deploy_website (both deploy a site, one multi-file and one single-file), and get_project versus get_project_files versus list_projects require careful reading.
Every tool follows a consistent snake_case verb_noun pattern: create_*, get_*, list_*, delete_*, update_*, upload_*, assign_to_project, unassign_from_project, configure_chatbot. There are no camelCase names, vague verbs, or mixed conventions.
At 29 tools, this exceeds the comfortable MCP surface and crosses into the 'too many' range. The breadth is somewhat justified by the number of subdomains (projects, files, forms, data, bookings, chatbot, media), but several getters and listers could be consolidated without losing capability.
The tool set covers a full website build lifecycle: account checks, content modeling, media upload, deploy, assignment, chatbot configuration, and post-deploy file edits. Minor gaps remain: booking pages and form settings are intentionally read-only via the MCP, and there is no chatbot deletion or teardown tool.