Skip to main content
Glama

table

Profile and query CSV/TSV/JSON/JSONL/Markdown data with filters, selections, aggregates, sorting, joins, and limits; output in multiple formats.

Instructions

Query CSV/TSV/JSON/JSONL/Markdown tables. No options = profile. where ["age > 30","city = Berlin","name ~ ^A","x is empty"], select, group_by + aggregate (count sum avg min max median count_distinct list; "sum(x) as t"), sort ["x desc"], distinct, join_path+on, limit, output, out_path.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "table"
  }
}

Input Schema

NameRequiredDescriptionDefault
onNocol or left=right
howNo
pathNoor a file
sortNo
textNo
limitNo
whereNo
formatNo
outputNo
selectNo
distinctNo
group_byNo
out_pathNo
aggregateNo
delimiterNo
join_pathNo
no_headerNo
overwriteNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.2

TDQS

B3.3/5.0
Behavior2/5

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

The only annotation is destructiveHint=false, so the description carries most of the behavioral burden. It hints at file output via 'output, out_path' but says nothing about whether writing to out_path overwrites, what overwrite does, or how results are returned/profiled. For a tool with 18 params and a write path, this is thin.

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?

Dense and front-loaded: the core purpose comes first, then a compact enumeration of modes with inline examples. The telegraphic style is efficient, though the bare comma list makes some clauses harder to parse than necessary.

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?

Given 18 optional params, no output schema, and very low schema coverage, the description covers a good share of the query surface with examples. However, the source-input params (path vs text vs join_path), the profiling default's return shape, and overwrite/file-writing semantics are not explained, leaving real gaps for a tool this complex.

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

Parameters4/5

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

Schema coverage is only 11%, so the description must compensate, and it does: it gives concrete syntax for where (comparison, equality, regex '~', 'is empty'), aggregate function names plus 'sum(x) as t' aliasing, sort syntax 'x desc', and mentions select, group_by, distinct, join_path+on, limit, output, out_path. It leaves how, path, text, format, delimiter, no_header, and overwrite 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?

States a concrete verb+resource: 'Query CSV/TSV/JSON/JSONL/Markdown tables', and names the input formats, which separates it from siblings like json, markdown, and table_convert. It does not explicitly say how it differs from those siblings, keeping it below a 5.

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

Usage Guidelines3/5

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

'No options = profile' gives a useful default behavior, and the parameter list implies the supported query modes. It never states when to reach for this over table_convert or json, nor any prerequisites/exclusions.

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