Show the user how to add knowledge-base documents (PDFs, docs) to their website chatbot, and report what is already uploaded. Files are uploaded through the returned interface — this tool does not accept file contents directly.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Why the user wants to add documents — shown as context |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavior not visible in annotations: the tool does not accept file contents directly and instead returns an interface through which files are uploaded. It also clarifies the reporting side by stating it reports what is already uploaded. This goes beyond the minimal readOnly/destructive hints.
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 two tight sentences with no filler. The primary action and the critical limitation (no direct file upload) are front-loaded and each sentence contributes necessary information.
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 tool with one optional parameter and no output schema, the description covers the essential behavior: what it does, what it reports, and its key constraint. It does not specify the format of the returned interface or the report, but that is not essential for an agent to invoke the tool correctly.
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 only parameter, 'reason', is fully documented in the schema with a clear description, so the schema carries the semantic load. The tool description does not add further detail about how the reason is used, but it does clarify why no file-content parameter exists, which indirectly supports the parameter design.
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 states the action: show the user how to add knowledge-base documents to their chatbot and report existing uploads. It is specific about the resource (chatbot knowledge base) and the key behavior, but it does not explicitly distinguish itself from the sibling list_chatbot_documents, which also involves reporting uploaded documents.
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 intended use case is implied by the first sentence: when the user wants to add knowledge-base documents to a chatbot, this tool shows them how. However, it does not mention alternatives such as list_chatbot_documents or explain when to prefer this tool over other upload-related 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.
