Skip to main content
Glama
cortex-local-memory

cortex-local-memory

cortex_plan

Builds a concrete retrieval plan for a question or task, specifying which queries to run, which mode to use, and what to look for, without performing the search itself.

Instructions

Given a question or task, return a concrete retrieval plan (which queries to run, which mode, what to look for). Does not itself search.

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": {
      "question": "<question>"
    },
    "name": "cortex_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesThe user question or task to plan retrieval for

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.0.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the key trait: this is a planning-only tool that returns no search results, so an agent won't mistake its output for data. It does not cover cost, latency, or whether the plan is deterministic, which keeps it from a 5.

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 compact sentences, front-loaded with the action and immediately followed by the negative constraint. No filler.

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

Completeness4/5

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

For a single-parameter planning tool with no output schema, the definition covers what it produces and what it does not do. A note on how to consume or execute the returned plan would close the remaining gap.

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

Parameters3/5

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

Only one parameter and schema coverage is 100%, so the schema already defines 'question' adequately; the description adds no format, length, or scoping guidance beyond it. Baseline 3 applies.

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

Purpose5/5

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

Names a specific verb and output (return a concrete retrieval plan) plus the contents of that plan (queries, mode, what to look for), and explicitly carves out the non-behavior 'Does not itself search,' which separates it from cortex_search and sibling search tools.

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

Usage Guidelines4/5

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

Establishes clear context — use it when you have a question or task and need a retrieval plan first — and adds an explicit exclusion by stating it performs no searching itself. It stops short of naming a specific alternative to call after the plan, so the agent must infer that cortex_search executes it.

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