Skip to main content
Glama

Look at a table

preview_table
Read-onlyIdempotent

Shows the rows a house table will hold, before the file is written. Use it whenever a file's words need a table's figures: a report's opening paragraph, a slide's title, a deck's first slide. A counted table (buyers, advisers, deals_by_year) has its figures only once every row is read, so look at it first, write the words from what comes back, and make the file once. Never make a file to learn its figures and then make it again.

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": {
      "table": "<table>",
      "from": "<from>"
    },
    "name": "preview_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxNoHow many rows to show. Ten when left out.
fromYesThe lookup that fills it, exactly as the file's table will give it.
tableYesThe house table to look at.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / table / enum
      Previous value: -[
      -  "deals",
      -  "firm_deals",
      -  "buyers",
      -  "advisers",
      -  "deals_by_year",
      -  "firms",
      -  "funds",
      -  "companies",
      -  "new_offerings",
      -  "placement_agents",
      -  "found_companies",
      -  "people",
      -  "parties"
      -]New value: +[
      +  "deals",
      +  "firm_deals",
      +  "buyers",
      +  "advisers",
      +  "deals_by_year",
      +  "firms",
      +  "funds",
      +  "companies",
      +  "new_offerings",
      +  "found_buyers",
      +  "placement_agents",
      +  "found_companies",
      +  "people",
      +  "parties"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / table / enum
      Previous value: -[
      -  "deals",
      -  "firm_deals",
      -  "buyers",
      -  "advisers",
      -  "deals_by_year",
      -  "firms",
      -  "funds",
      -  "companies",
      -  "found_companies",
      -  "people",
      -  "parties"
      -]New value: +[
      +  "deals",
      +  "firm_deals",
      +  "buyers",
      +  "advisers",
      +  "deals_by_year",
      +  "firms",
      +  "funds",
      +  "companies",
      +  "new_offerings",
      +  "placement_agents",
      +  "found_companies",
      +  "people",
      +  "parties"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / table / enum
      Previous value: -[
      -  "deals",
      -  "firm_deals",
      -  "buyers",
      -  "advisers",
      -  "deals_by_year",
      -  "firms",
      -  "funds",
      -  "companies",
      -  "people",
      -  "parties"
      -]New value: +[
      +  "deals",
      +  "firm_deals",
      +  "buyers",
      +  "advisers",
      +  "deals_by_year",
      +  "firms",
      +  "funds",
      +  "companies",
      +  "found_companies",
      +  "people",
      +  "parties"
      +]
  4. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare this tool to be read-only, idempotent and non-destructive, so safety is covered elsewhere. The description adds real behavioral context that annotations cannot: counted tables have figures only once every row is read, which explains why this preview exists and why it must come before file creation. It stops short of saying what the returned preview looks like or how large it is.

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?

The purpose comes first and the workflow constraint follows immediately, with no filler sentences. The closing idea is restated twice ('make the file once', 'never make a file to learn its figures and then make it again'), which is emphatic but slightly redundant.

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 a read-only preview tool with a fully documented three-parameter schema and no output schema, the description covers what an agent needs: when to call it, what it costs, and how it fits into the write workflow. The only gap is the shape of what comes back, which the absence of an output schema leaves undescribed.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents table, from, and max, including how many rows to show and which nested list to pull from. The description adds no parameter-level detail, such as how many rows the preview returns or how a lookup's result is shaped. With the schema doing all the work, the baseline 3 is appropriate.

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?

The description gives a specific verb and resource: it shows the rows a house table will hold, before the file is written. It names the enumerated table families (buyers, advisers, deals_by_year) and clearly separates this preview step from producing the finished file, so an agent can tell it apart from make_artifact and the search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is spelled out with concrete contexts (a report's opening paragraph, a slide's title, a deck's first slide) and an explicit anti-pattern: never make a file just to learn its figures and then make it again. The correct sequence is stated directly: look first, write the words from what comes back, then make the file once.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources