Skip to main content
Glama

Block a table or column

block

Prevent an entire table or a single column from being sent to the AI, so sensitive data stays hidden from every query.

Instructions

Block a table, or one column of it, from the AI for good: it is never sent, whatever the query. Leave column out to block the whole table. Use this when the user asks to hide or protect data.

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": {
      "source": "<source>",
      "table": "<table>"
    },
    "name": "block"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYes
columnNo
sourceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false; the description adds the crucial behavioral fact that blocked data is never sent whatever the query, which tells the agent the effect is scope-wide rather than per-request. Gaps remain: it does not say whether the block is reversible or how to undo it, nor whether elevated permissions are required for a write operation.

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?

Two short sentences, front-loaded with the core effect, followed by the parameter rule and the usage trigger. No filler or redundant restatement of the title.

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?

No output schema and only sparse annotations, so the description must carry more weight. It conveys the effect and the column-omission rule adequately, but leaves open the required `source` parameter's meaning, the reversibility of a block, and required permissions for a non-read-only operation.

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 coverage is 0%, so the description carries the full burden. It usefully explains the optional `column` parameter's conditional meaning (omitted = whole table), but `source` is a required parameter that is never explained, and the identifier format for `table`/`column` is unstated. Two of three parameters are only partly or not at all clarified.

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 (block) and resource (table or one of its columns) plus the concrete effect: the data is never sent to the AI regardless of query. This is far more than a restatement of the name, though it never names a sibling or explicitly contrasts itself with query or list_rules, so an agent must infer its place in the catalog.

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?

Provides an explicit trigger: 'Use this when the user asks to hide or protect data,' which maps a user intent to this tool. It also states the parameter variation ('Leave `column` out to block the whole table'). It stops short of saying when NOT to use it or pointing at an alternative (e.g., a rule-listing or unblock path).

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