Skip to main content
Glama

Update an existing row

update_row

Updates specific columns in an existing Google Sheets row without overwriting other cells. Target the row by number or by matching a unique value, such as an ID.

Instructions

Modifies only the named columns of an existing row, leaving every other column untouched. This is the right tool for changing a status or fixing a field in a register: unlike write_range it does not overwrite the whole row. The row is identified either by number (from find_rows) or by matching a value in a column.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowNoAbsolute row number, as returned by find_rows.
matchNoAlternative to row: locate the row by a unique value, e.g. an ID.
sheetYesTab name, e.g. 'Log'.
updatesYesOnly the columns to change.
headerRowNo
spreadsheetIdYesSpreadsheet ID, or its full URL. The ID is the segment between /d/ and /edit in the URL.
valueInputOptionNoUSER_ENTERED parses values as if typed by hand (formulas, dates, numbers). RAW stores them literally as strings.USER_ENTERED

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior3/5

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

Without annotations, description carries full burden. It states the non-destructive scope (only named columns), which is valuable. However, it doesn't cover authentication needs, rate limits, error behavior, what happens if row/match not found, or reversibility. Some behavioral context is present but incomplete.

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 sentences, front-loaded with the core behavior (partial column update), then the sibling contrast and row identification. Every sentence earns its place with no waste.

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?

Given 7 parameters, nested objects, and no output schema, the description covers the key behavioral trait (partial update) and row identification alternatives. It could mention what happens on missing row/match or the valueInputOption implications, but schema handles most parameter details.

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 86%, so schema already documents most parameters. The description adds meaning about row identification ('by number (from find_rows) or by matching a value in a column') and the partial-update semantics of 'updates'. This goes beyond the schema's per-field descriptions.

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 (modifies) and scope (only named columns, other columns untouched), and distinguishes itself from write_range by contrast. Siblings like update_cell and write_range are implicitly differentiated by scope description.

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?

Explicitly says when to use this tool ('changing a status or fixing a field') and names the alternative (write_range) with the condition that selects it ('unlike write_range it does not overwrite the whole row'). No explicit when-not conditions, but the alternative contrast is clear.

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