Табуля

files_search

Read-onlyIdempotent

Searches cell values across a Tabulya spreadsheet file and returns the matching cells, so you can locate data without reading whole sheets. Searches every sheet unless 'sheet' is given. Each hit is { sheet, cell (A1), x, y (1-based coords), value }. Read-only; searches the file's latest live state. Options: case_sensitive; whole_cell (match only cells whose entire value equals the query); search_code (also match the source of code cells, not just their displayed output). Signature: files_search(file_uuid, query, sheet?, case_sensitive?, whole_cell?, search_code?).

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>",
      "query": "<query>"
    },
    "name": "files_search"
  }
}

Input Schema

Name	Required	Description
`query`	Yes	Text to find in cell values (substring match by default).
`sheet`	No	Restrict the search to this sheet (defaults to all sheets).
`file_uuid`	Yes
`whole_cell`	No	Match only cells whose entire value equals the query.
`search_code`	No	Also search the source of code cells, not just their displayed output.
`case_sensitive`	No

Output Schema

Name	Required	Description	Default
`count`	Yes
`results`	Yes
`file_uuid`	Yes
`truncated`	Yes
`server_tables_skipped`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real value: it discloses that it searches the file's 'latest live state' and that scope defaults to all sheets. The hit shape is restated but the output schema already covers that, so it is not extra credit.

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?

Front-loaded with purpose and scope, then defaults, return shape, and options — a sensible information hierarchy. The trailing 'Signature:' line largely duplicates the input schema, which is mild redundancy.

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

Completeness5/5

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

For a read-only search with an output schema and mostly documented params, the description covers scope defaults, matching modes, and data freshness. Nothing an agent needs to invoke it correctly is missing.

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 explains the non-obvious semantics of whole_cell and search_code (code source vs displayed output) in terms beyond the schema's terse phrasing. case_sensitive is only listed as an option with no explanation, leaving one gap, though the name is largely self-describing.

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+resource ('Searches cell values across a ... spreadsheet file and returns the matching cells') and contrasts the scope against reading whole sheets, which cleanly separates it from siblings like files_read. An agent can identify the operation and its scope without opening the 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?

Gives a clear usage rationale ('so you can locate data without reading whole sheets') and a default behavior rule ('Searches every sheet unless 'sheet' is given'). It implies the files_read alternative but does not name any sibling tool explicitly or state when-not to use it.

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?