Skip to main content
Glama

Panel: preview a column's level

level_preview
Read-only

Previews how a result column appears to the AI at the chosen anonymisation level so you can verify masking before sharing. App-only; the model never sees this preview.

Instructions

The user chose Anonymise or Totals only from a column's menu in the results panel: that column of the result as the AI would get it at that level ("anonymised" or "totals"). Never for a column the user keeps from the AI. App-only: the model never sees this tool or its result.

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": {
      "pull_id": "<pull_id>",
      "column": "<column>",
      "level": "<level>"
    },
    "name": "level_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
levelYes
columnYes
pull_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, non-destructive, closed-world), and the description adds non-obvious context: this is an app-only affordance whose result the model never sees, and the output reflects the AI's reduced view at the selected level. That is meaningful behavior beyond the annotations, though the 'model never sees this tool' framing is unusual and slightly confusing for a tool being described to a model.

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?

It is short and the gating condition comes first, but the opening sentence is grammatically tangled ('that column of the result as the AI would get it at that level'), forcing a re-read. The closing app-only note is useful but sits awkwardly after the exclusion rule rather than with the purpose statement.

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

Completeness3/5

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

The description conveys what the preview returns (the column as the AI would see it at that level), which partly substitutes for the missing output schema. However, with three undocumented required parameters and no indication of the pull_id's provenance or the column identifier format, an agent lacks enough to invoke it confidently in edge cases.

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

Parameters2/5

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

Schema description coverage is 0% and none of the three required parameters is documented in the schema. The description partially compensates for 'level' by supplying the concrete values 'anonymised' and 'totals', but 'column' (name? index? id?) and 'pull_id' (what a pull is, where to get one) are left entirely unexplained.

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?

The description names a specific action and resource: previewing one column of a result as the AI would receive it at a given anonymisation level. The scope (single column, at a level, triggered from the column menu) is clear enough to distinguish it from list-oriented siblings like panel_rows or kept_rows, though no sibling is named explicitly.

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?

It gives a concrete trigger ('the user chose Anonymise or Totals only from a column's menu') and an explicit exclusion ('Never for a column the user keeps from the AI'), which is real when/when-not guidance. It stops short of naming an alternative tool for the excluded case, so the agent must infer what to use instead.

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