Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis · Data Analyst — Data Memory Script

data_memory_script

Open a researcher's analysis script to reuse its paths, data loading, cleaning steps and column names before writing new code, so you stop guessing definitions or asking for names().

Instructions

Open the CODE of one of the researcher's analysis scripts.

Use it on the templates `data_memory` names, before writing a new script:
reuse their paths, loading, cleaning, column names and definitions instead
of guessing them or asking the researcher to run names(). Works for .R,
.Rmd, .qmd and .py files inside the folders Metis learns from — never for
a data file. A bare file name is enough when it is unique.

Args:
    path: the script's path as data_memory showed it, or its file name.

Input Schema

NameRequiredDescriptionDefault
pathYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.7

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are present, so the description carries the full burden, and it delivers the key traits: accepted extensions (.R, .Rmd, .qmd, .py), scope limited to folders Metis learns from, refusal of data files, and short-name resolution ('a bare file name is enough when it is unique'). It does not say what happens when a bare name is ambiguous or whether files are truncated, 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?

Front-loads the action in the first sentence, then usage, scope, and parameter guidance in a logical order. Every clause carries information — file types, exclusion, name resolution — with no restatement of the name or title.

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?

With an output schema present, return values need no explanation, and the description covers purpose, scope, file types, and argument form for a one-parameter read tool. The only real gap is behavior on ambiguous bare names, which is hinted at but not resolved.

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

Parameters4/5

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

The single parameter has 0% schema description coverage, so the description must compensate; it does, by specifying the expected form ('the script's path as data_memory showed it, or its file name') and noting bare names are accepted when unique. It adds genuine meaning beyond the bare {path: string} schema.

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?

States a specific verb and resource — 'Open the CODE of one of the researcher's analysis scripts' — and explicitly distinguishes from the sibling data_memory_dataset with 'never for a data file.' An agent can tell what it retrieves (script source, not data or metadata) without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use ('on the templates data_memory names, before writing a new script'), the motivation (reuse paths, loading, cleaning, column names), and an explicit exclusion routing data files to a different tool. Alternatives to the tool's use ('instead of guessing them or asking the researcher to run names()') are also named.

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

Deploy Server

Other Tools