Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis — Find Viz

find_viz

Search saved visualization recipes and styles before building a chart, map, diagram, flow, table, or layout. Use intent and kind filters to find matching data contracts and proven style candidates.

Instructions

Find saved recipes and styles before building anything. Call this FIRST.

This is the tool the whole library exists to serve. Eleven agent context
files were once written and never read once — a store nothing queries is
worse than no store, because it looks like progress. So: consult this before
designing a figure, not after.

Each recipe prints a **Needs** line: the roles its data contract demands. To
check a specific dataset against one, propose a role -> column mapping and
confirm it with `check_viz_fit`. This tool deliberately will not guess that
mapping — a name-similarity guess was tried here and could not tell a
fitting dataset from an unfitting one.

Args:
    kind: chart | map | diagram | flow | table | layout. Blank = all.
    intent: Free text matched against names, one-liners, encodings and
        media, e.g. "show dispersion not averages", "for a paper".
    limit: Max recipes to return.

Returns:
    Matching recipes with their contracts and track records, plus candidate
    styles ranked by how often they were loved.

Input Schema

NameRequiredDescriptionDefault
kindNo
limitNo
intentNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries the burden, and it does disclose a real behavioral limit: it deliberately will not guess role->column mappings because a name-similarity heuristic proved unreliable. It also describes the 'Needs' line each recipe emits. It does not state read-only status explicitly, though 'find' implies retrieval.

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

Conciseness3/5

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

The purpose and 'Call this FIRST' are correctly front-loaded, but the middle paragraph ('This is the tool the whole library exists to serve... Eleven agent context files were once written and never read once...') is motivational filler that delays the operational content an agent needs. The Args and Returns blocks are tight and well-structured.

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?

An output schema exists so return values need not be detailed, params are fully covered, and the mapping limitation plus the check_viz_fit handoff close the main gap. Missing: whether results are ordered or capped in ways beyond limit, and no mention of what tracks/contracts are shown beyond a brief phrase.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate and does: it enumerates the full kind vocabulary with blank meaning 'all', explains intent is free text matched against names, one-liners, encodings and media with concrete example queries, and defines limit as max recipes returned. This is more than the schema provides.

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 ('Find saved recipes and styles') and scopes retrieval versus authoring siblings like save_viz_recipe/save_viz_style. It also draws an explicit boundary with check_viz_fit, saying this tool will not resolve role->column mappings itself, so an agent can pick between them without opening a schema.

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?

'Find ... before building anything. Call this FIRST' gives a clear trigger condition, and the mapping note routes the follow-up step to check_viz_fit. The only gap is that viz_library_overview is a plausible alternative for a high-level view and is never mentioned or excluded.

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