Skip to main content
Glama

Metis — Record Viz Use

record_viz_use

Record a rendered visualization recipe, style, dataset, and verdict to build a track record that ranks styles and prevents repeated debates.

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. "cohort-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.

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": {
      "recipe": "<recipe>"
    },
    "name": "record_viz_use"
  }
}

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

A4.2/5.0
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 important behavioral trait no structured field conveys: the record feeds a ranking, and a fabricated verdict corrupts it. It also states the return shape ('confirmation plus the recipe's running track record'). It does not say whether repeat logging duplicates entries, or what happens on an unknown recipe slug.

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 one-line purpose, then a short justification for the tool's existence, then Args and Returns blocks — easy to scan and well ordered. The 'every session re-argues which style to reach for' clause is slightly florid but does earn its place as behavioral context.

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 an 8-parameter write tool with zero annotation coverage, the description covers purpose, all parameters, enum values, a data-integrity warning, and the return shape (which the output schema would have covered anyway). Only idempotency/duplicate-handling and error behavior remain undisclosed.

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% across 8 parameters, and the description compensates completely: every param is explained, including cross-table references (recipe → viz_recipes.slug, style → viz_styles.slug) and examples ('cohort-analysis'). Critically, it supplies the verdict enum (loved | fine | wrong) that the schema itself lacks, which an agent could not otherwise infer.

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: 'Log that a recipe was rendered — and what the researcher thought of it,' plus a crisp rationale ('the table that answers styles that we used'). This clearly separates it from the curation siblings (save_viz_recipe, save_viz_style) by framing it as the evidence-recording step, though no sibling is named explicitly to route an agent between find_viz / check_viz_fit / record_viz_use.

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?

The trigger is clear — call it after a render has actually happened, and it explicitly warns 'Leave blank until he has actually said — a guessed verdict poisons the ranking it feeds,' which is real usage guidance. What is missing is any exclusion or explicit pointer to the adjacent tools (find_viz, check_viz_fit) that precede or follow 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