delete_documentDelete a document from a project.
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document id (uuid). | |
| projectId | Yes | Project id (uuid). |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes |
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?
The destructive nature is already conveyed by the `destructiveHint: true` annotation, so the description does not need to repeat it. The phrase 'from a project' adds scoping context not present in annotations. However, no additional behavioral details such as permanence, cascading effects, or authorization requirements are disclosed.
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 one concise sentence that adds the project scoping beyond the title. There is no unnecessary wording or duplicated detail from the schema.
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 simple two-parameter deletion tool, the description, schema, and annotations together provide enough information to invoke the tool correctly. The eisting output schema covers return values, and destructiveHint covers safety. Missing alternative routing is the only notable gap, which is already accounted for in usage guidelines.
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 input schema has 100% description coverage, including UUID formats for `projectId` and `docId`. The tool description adds no parameter-specific information, but the schema already fully documents the parameters, waranting the baseline score of 3.
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 clearly identifies the operation as deleting a document, specifies the resource (document), and scopes it to a project. This distinguishes it from sibling tools like delete_org and delete_project, and from update_document.
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?
No guidance is provided about when to use this tool instead of alternatives like update_document or create_document. The context is obvious from the verb, but there is no explicit or implicit discussion of alternatives or prerequisites.
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 target a distinct resource and action, and the descriptions clearly explain boundaries. However, list_diagrams/list_documents and get_board/get_board_image are two pairs that both concern the same underlying resource, so an agent could initially select the wrong one without reading carefully.
Nearly all tool names are snake_case verb_noun pairs such as create_project, update_document, and unpublish_listing, which is very consistent. The exceptions are bare 'draw' and the non-pattern 'whoami', so it is not a perfect 5.
With 38 tools, the surface exceeds the 25+ threshold and spans orgs, projects, documents, board drawing, membership, and marketplace publishing. While each subdomain is individually reasonable, the aggregate is heavy and likely to overwhelm an agent; several related actions could be grouped or exposed more sparingly.
The set covers the main lifecycle: org/project/document CRUD, board rendering and editing, member management, and template publish/use/update. Minor gaps remain—there is no get_project single-resource read, and groups/links/notes are manipulated only through the generic update_board rather than dedicated tools—but these are workable.