Computes the RAG index for a knowledge base document, enabling it for retrieval-augmented generation and semantic search.
Compute Rag Index.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | ||
| documentation_id | Yes | The id of a document from the knowledge base. This is returned on document addition. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the agent knows this is a non-idempotent mutating operation, but the description adds nothing on top of that. It never says whether the call kicks off an indexing job, whether it is synchronous or async, whether it requires the knowledge base to already exist, or what side effects it produces.
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 words and a period. This is under-specification rather than conciseness — there is no front-loaded scope, no object of the computation, and nothing for the agent to act on.
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?
A tool with two required parameters, a mutating/non-idempotent annotation profile, and no output schema needs far more than three words. The description leaves the operation's trigger semantics, prerequisites, and return behavior entirely unexplained.
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 only 50%: documentation_id is documented, but the model parameter (an enum of two embedding models) has no description anywhere. The description supplies no parameter meaning at all, so it fails to compensate for the coverage gap.
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 'Compute Rag Index.' is a near-tautology that restates the tool name in different words and never resolves the ambiguity between the name ('status', implying a read) and the verb ('compute', implying a write/trigger). It gives no basis for choosing it over the many siblings in the same domain (get_rag_indexes, get_rag_index_overview, get_or_create_rag_indexes, delete_rag_index).
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?
There is no when-to-use, when-not-to-use, prerequisite, or alternative-tool guidance of any kind. This is especially costly here because at least three siblings cover overlapping RAG-index territory, and an agent has nothing to route on.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.