Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis — Record Viz Use

record_viz_use

Log a rendered visualization recipe with its style, dataset, output, and researcher verdict so Metis can rank which styles work and stop re-arguing choices.

Instructions

Log that a recipe was rendered — and what the researcher thought of it.

The table that answers "styles that we used". Without it the library holds
intentions and no evidence, so nothing can be ranked and every session
re-argues which style to reach for.

Args:
    recipe: viz_recipes.slug.
    style: viz_styles.slug.
    dataset: What it was rendered against, in plain words.
    project_id: e.g. "angola-hat-analysis".
    output_path: Local file written.
    artifact_url: If it was published as an Artifact.
    verdict: loved | fine | wrong. Leave blank until he has actually said —
        a guessed verdict poisons the ranking it feeds.
    note: What worked, or what went wrong.

Returns:
    Confirmation plus the recipe's running track record.

Input Schema

NameRequiredDescriptionDefault
noteNo
styleNo
recipeYes
datasetNo
verdictNo
project_idNo
output_pathNo
artifact_urlNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden and does a reasonable job: it warns that a guessed verdict 'poisons the ranking it feeds' (a data-integrity side effect) and briefly describes the return value as 'confirmation plus the recipe's running track record.' It omits permissions, duplicate-log behavior, and whether existing records are mutated.

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

Conciseness4/5

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

Front-loaded with the action, then a short rationale, then a clean Args block. The middle paragraph is slightly rhetorical ('every session re-argues which style to reach for') but it earns its place by justifying why the log matters. Minor trimming possible, no real waste.

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 needn't be spelled out, and all 8 inputs are explained. What is missing is edge-case behavior — deduplication on repeated calls, whether a later call can overwrite verdict/note, and any permission requirements for writing to the ranking table.

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 coverage is 0% with 8 parameters, yet the description documents every one: recipe and style are named as slug references into specific tables, project_id gets a concrete example format, and verdict is given an enum (loved | fine | wrong) that the schema itself lacks. This fully compensates for the empty schema descriptions.

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 ('Log that a recipe was rendered') plus the secondary payload (the researcher's verdict). This clearly separates it from siblings like save_viz_recipe (authoring a recipe) or save_viz_style (authoring a style) — this is the evidence/usage-record tool.

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?

Gives a clear trigger context: use it when a recipe has actually been rendered, because without it 'nothing can be ranked.' It does not explicitly name the adjacent tools (save_viz_recipe, find_viz, check_viz_fit) or state exclusions, so an agent must infer the boundary rather than read it.

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