Remove the project's backend and revoke its data access. The app's own stored data is KEPT, so this is not a way to erase submissions. The site's pages are untouched and keep serving.
| Name | Required | Description | Default |
|---|---|---|---|
| project_guid | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior, and it does exceptionally well. It states what is destroyed (backend, data access), what is preserved (stored submissions, site pages), and explicitly corrects a dangerous misconception about the data being erased.
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?
Three short sentences accomplish a high level of guidance with zero filler. The action is front-loaded in the first sentence, with the two most important caveats following in subsequent sentences. Every sentence earns its place.
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 destructive tool, the description is highly complete: it states the action, the data that is kept, and the unaffected pages. An output schema is present, so return-value details are not required. It only lack nuance about whether the operation is reversible or how to re-establish a backend, which would be useful but not necessary.
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 schema provides no description for project_guid (0% coverage), so the description must compensate. It does by contextualizing the parameter through 'the project's backend' and 'its data access,' making clear the identifier refers to an existing project. It still leaves minor gaps, such as where to obtain the GUID or how to validate it, but the meaning is clear enough for a self-explanatory project identifier.
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 opens with a specific verb and resource: 'Remove the project's backend and revoke its data access.' It immediately differentiates the tool from siblings such as delete_project, delete_page, and delete_asset by clarifying that the backend, not the project or pages, is being removed, and that stored data is preserved.
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?
The description provides explicit when-not-to-use guidance: the app's stored data is kept, so this is not a way to erase submissions. It falls short of a 5 because it does not name alternative tools or conditions for when to choose this over siblings like create_backend or delete_project, instead relying on the agent to infer them.
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 pair a distinct action with a distinct resource and long descriptions make intent clear. Still, `search_domains` already provides exact-domain checks, overlapping with `check_domain`, and the `create_project` vs `create_new_site` vs `create_page` cluster takes careful reading.
The vast majority are snake_case verb_noun: list_projects, create_project, delete_page, get_preview_url, write_asset, query_database, publish_website. The only visible outlier is whoami, but it is standard enough that it does not disrupt predictability.
At 36 tools this is meaningfully heavier than the rubric's 'too many' threshold, even though the scope spans websites, backends, domains, gallery images, and databases. It makes selection harder and a sizeable portion of the surface is niche or lifecycle internal.
The core site lifecycle is well covered: project, htmlmanag, assets, preview/publish, validation, deletion, uploaded images, backend files/logs, database reading, domain search and purchase linking. Workable non-critical gaps exist, e.g. no separate project metadata rename and no direct way to delete database rows or a database outside of deleting the project.