Skip to main content
Glama

Update custom column value

well_update_custom_column_value
Destructive

Set or clear the value of one cell of a custom column: one column, on one record of the column's view.

Use this tool when the user asks to fill in, change or clear what a custom column holds for one record (e.g. "put Scalify and Mehdi Amrani in the Contreparties column of this deal", "clear the owner of this company").

REQUIRED: custom_column_id, record_id, value

  • record_id: the id of the record of the column's view (a project, a company, a person, ...).

  • value: shaped by the column type. A record_reference column takes { root, id } naming a record of one of the column's reference targets, or a list of { root, id } when the column holds a list. A column that targets several roots (for example people and companies) takes records of any of them in the same list. null clears the cell.

A column Well computes (an AI or rule column) or a connected tool syncs cannot be typed by hand: the call is refused.

Returns { success: true, custom_column_id, record_id, value } on success, or { success: false, error } on failure.

Input Schema

NameRequiredDescriptionDefault
valueYesThe cell value, shaped by the column type: text a string; number a number; amount { value, currency }; date YYYY-MM-DD; boolean true or false; single_select a label; multi_select a list of labels; record_reference { root, id } or, on a list column, a list of { root, id }. null clears the cell
record_idYesThe UUID of the record of the column's view whose cell is written (required)
workspace_idNoTarget workspace. Omit when the token authorizes one workspace. Required when it authorizes several — a write lands in exactly one workspace and this call would not say which.
conversation_idNoThe conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation.
idempotency_keyNoOptional client-supplied key. A retried write with the same key returns the original result instead of re-applying the operation.
workspace_scopeNoRestrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace.
custom_column_idYesThe UUID of the custom column (required)

Output Schema

NameRequiredDescriptionDefault
codeNo
errorNo
valueNo
successYes
record_idNo
reply_linesNo
conversation_idNoThe conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
near_candidatesNo
newly_connectedNoTools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: "<name> is connected.". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.
custom_column_idNo
conversation_id_noteNoPresent only when the server opened a fresh lane, stating that no choice recorded earlier was read.
conversation_id_sourceNoWhere the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.
near_candidates_truncatedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds real value on top: null clears the cell, hand-typing into computed or connector-synced columns is refused, and the failure mode returns { success: false, error }. It doesn't discuss permission requirements or whether clearing is recoverable, which for a destructive write would be useful.

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 the core action, then a usage paragraph, then a REQUIRED list, then behavioral caveats. Structure is clean, though the trailing returns line duplicates what the output schema already provides and could be trimmed.

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?

With 7 parameters at 100% schema coverage, an output schema, and full annotations, the description covers what's needed: the three required params, the value-shaping rule, the refusal condition for computed/synced columns, and null-clearing semantics. No essential calling information is missing.

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 coverage is 100%, so the schema already documents value shapes, record_id UUID format, and the workspace/conversation/idempotency keys, which sets the baseline at 3. The description does add one nuance not in the schema — that a multi-root column accepts records of any target root in the same list — but otherwise largely restates the value-shape rules.

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?

The first line gives a precise verb+resource+scope: 'Set or clear the value of one cell of a custom column … on one record of the column's view.' That distinguishes writing a cell value from the sibling well_update_custom_column (which edits the column definition) implicitly, but no sibling is named explicitly, so it falls short of full differentiation.

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?

It states the triggering user intents with concrete examples ('put Scalify and Mehdi Amrani in the Contreparties column', 'clear the owner of this company') and gives an important exclusion: computed/AI/rule columns and synced columns are refused. The only gap is that no alternative sibling is named for cases where this tool is the wrong choice.

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