Skip to main content
Glama

rag_pipeline_plan

Read-onlyIdempotent

Plan retrieval-augmented generation pipelines from corpus facts, covering chunking, embedding, indexing, authorization, evaluation, and cost drivers without choosing a vendor.

Instructions

Plan a retrieval-augmented generation pipeline from corpus facts: chunking, embedding, indexing, authorization, evaluation and cost drivers, with open questions. No vendor is chosen for you.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "useCase": "<useCase>",
      "corpus": "<corpus>",
      "authorization": "<authorization>"
    },
    "name": "rag_pipeline_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
corpusYes
useCaseYes
authorizationYes
latencyBudgetMsNo
citationsRequiredNo

Output Schema

NameRequiredDescriptionDefault
kindNo
sizingNo
stagesNo
sourcesNo
useCaseNo
nextToolsNo
validatedNo
limitationNo
costDriversNo
openQuestionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.5.0
    • removedInput schema / properties / corpus / additionalProperties
      Removed value: -false
    • changedInput schema / properties / corpus / required
      Previous value: -[
      -  "documents",
      -  "averagePages",
      -  "formats",
      -  "updateFrequency",
      -  "languages"
      -]New value: +[
      +  "documents",
      +  "formats",
      +  "updateFrequency"
      +]
    • changedInput schema / required
      Previous value: -[
      -  "useCase",
      -  "corpus",
      -  "authorization",
      -  "latencyBudgetMs",
      -  "citationsRequired"
      -]New value: +[
      +  "useCase",
      +  "corpus",
      +  "authorization"
      +]
  2. First observedv0.4.1

TDQS

A3.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is met. The description adds non-obvious behavioral context not in the annotations: the output surfaces open questions and deliberately avoids vendor selection, telling the agent to expect an advisory, decision-neutral plan rather than a concrete stack.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero filler, front-loaded with the action and scope, and closing on the vendor-neutral constraint that matters most for interpreting the result.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the description adequately frames the plan's scope. However, for a tool with a nested corpus object and five inputs at 0% schema coverage, the absence of any parameter guidance leaves a real gap an agent must close by guesswork.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, yet it never names a single parameter. 'Corpus facts' and 'authorization' gesture at two of five inputs, but nothing explains latencyBudgetMs, citationsRequired, or what the authorization enum values mean for the plan — the agent must infer everything from raw enum names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Plan a retrieval-augmented generation pipeline') and enumerates the artifacts covered: chunking, embedding, indexing, authorization, evaluation, cost drivers, open questions. No sibling tool occupies this niche, but the description never names or contrasts an alternative, so it stops short of explicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the phrase 'from corpus facts' indicates this is for designing a new RAG pipeline rather than reviewing an existing one, and 'No vendor is chosen for you' hints at advisory output. There is no explicit when-to-use, when-not-to-use, or pointer to a related tool such as architecture_pattern or implementation_plan.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.