Табуля

files_table_delete

Destructive

Deletes columns or rows from INSIDE an existing data table (distinct from files_delete_rows_cols, which removes sheet-level rows/columns). cell: any cell inside the table. axis='columns' or 'rows'. index: 0-based position within the table. count: how many to remove (default 1). Server tables (rows on the tables service): rows are counted in the table's current sort and filter (at most 1,000,000 per call), and columns as files_context lists them. Requires edit permission. Signature: files_table_delete(file_uuid, cell, axis, index, count?, sheet?).

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": {
      "file_uuid": "<file_uuid>",
      "cell": "<cell>",
      "axis": "<axis>",
      "index": "<index>"
    },
    "name": "files_table_delete"
  }
}

Input Schema

Name	Required	Description
`axis`	Yes
`cell`	Yes	Any cell inside the table.
`count`	No	How many columns/rows to remove (default 1).
`index`	Yes	0-based table-relative position to delete from.
`sheet`	No	Sheet name (defaults to the first sheet).
`file_uuid`	Yes

Output Schema

Name	Required	Description	Default
`file_uuid`	Yes
`sequence_number`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, so safety is covered; the description adds permission requirements ('Requires edit permission') and per-call limits ('at most 1,000,000 per call'), which are real behavioral facts not in the structured fields. Row-index interpretation under the table's current sort and filter is a valuable caveat, though it does not say whether deleted data is recoverable or how remaining rows shift.

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 and sibling distinction are front-loaded, then parameter semantics, then the server-table caveat. It is dense but nearly every clause carries information; the trailing 'Signature:' line largely restates the schema and is the one expendable element.

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?

With an output schema present and annotations covering the destructive profile, the description supplies what is missing: permissions, the table-vs-sheet distinction, index semantics, and call limits. Minor gaps remain around post-deletion behavior (row/column shifting, deletion of the last row/column) that would matter for a destructive table mutation.

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 67%, and the description closes most of the gap: it clarifies that 'index' is 0-based and table-relative, that 'count' defaults to 1, and that row indices are evaluated against the current sort/filter while column indices follow files_context ordering. Only file_uuid and sheet are left to the schema, which is acceptable.

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?

States a specific verb and resource ('Deletes columns or rows from INSIDE an existing data table') and immediately names the sibling it must not be confused with, files_delete_rows_cols, plus the semantic difference (table vs sheet-level). An agent can route correctly without opening any schema.

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 exclusion against files_delete_rows_cols is explicit and the precondition 'cell: any cell inside the table' tells the agent the data must already be a table. It stops short of stating the positive routing rule (e.g., 'use this when the rows belong to a table object, use files_delete_rows_cols otherwise'), so the agent has to infer the inverse case.

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

All Табуля tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?