Skip to main content
Glama

Update record

update_record
DestructiveIdempotent

Patch fields on a record by id. Pass object_type + id + a patch object of the fields to change (a null value clears a custom field). Works for custom objects (shallow-merges into the record's data; owner-scoped unless the object is shared) AND the built-in objects with an update verb (account, contact, opportunity, subscription, task, touch — fix an activity's subject/summary/time/type — and report: refining a saved View the user already has is update_record(report, {id, patch:{definition}}), NOT a new one — only make a fresh View for a genuinely different perspective), where it routes to the same domain logic as the typed update tools. Returns the full updated record (fresh state). For a complete sequence plan, patch steps (retain saved ids), expected_revision (sequence mcp_revision), expected_steps [{id,revision}] for every live step, and request_id (UUID, reuse only for an identical retry). Steps save together; people still enrolled prevent changes to their timing, channels or order. Maintain verbs, each passed on its own: task subtasks replaces the whole checklist [{id?, title, done?}]; contact engaged:true confirms the person (a ratchet); opportunity board_rank:{before?, after?} orders a card in its current column; sequence_step position onto a neighbour's slot swaps the two (fenced while people are partway through).

When to use: Edit a record: pass object_type + id + a patch. Built-in objects route to the same domain logic as the folded typed update tools (e.g. advance a deal with {stage}, complete a task with {status:'done'}). Custom records are owner-scoped unless the object is shared. Retiring a converted lead (status 'converted', its account/contact/opportunity ids, converted_at and deleted_at) is the LAST step of lead conversion — see the lead conversion guide, an MCP resource at capable://guide/leads.

Example: Update opportunity : set stage to verbal.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesA uuid.
patchYesOnly the fields to change, key → new value; at least one key is required, and null clears a custom-object field (custom data is shallow-merged, not replaced).
object_typeYesObject key of the record being patched, e.g. account, contact, task, report, a custom object's key, or rollup / automation (admin-only; the id from describe_schema); an unknown key returns the valid types and writes nothing.
expected_revisionNoOptional record revision from a reviewed update; a changed record is refused without writing.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNo
recordNo
resultNo
updatedNo
object_typeNo
custom_field_definitionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Far exceeds the annotations: it discloses owner-scoping vs shared objects, null-clears-custom-field semantics, shallow-merge behavior, that the full updated record is returned, and rich per-verb semantics (engagement ratchet, board_rank, sequence_step swap fencing, subtasks replace). Annotations only give destructiveHint=true and idempotentHint=true; the description adds substantial behavioral context beyond them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and long, packing sequence-plan details, revision/step semantics and maintain verbs into one block. It is front-loaded with the core (patch fields by id), but several sentences are heavy run-ons that an agent must parse carefully, costing conciseness.

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?

For a highly complex, nested, multi-verb mutation tool, the description covers the key behaviors and routes to the reference guide. An output schema exists so return values need not be explained. It is thorough, though the density makes some conditions (sequence fencing, revision handling) easy to miss.

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 100%, so the baseline is 3, but the description adds real meaning: patch is a partial change (not replacement), null clears a custom field, and the object_type routing behavior. It adds value beyond the schema despite high coverage.

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 (patch fields on a record by id) and names the exact inputs (object_type + id + patch). It explicitly distinguishes routing behavior from siblings like create_record and the folded typed update tools, telling an agent exactly what this tool covers.

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 'When to use' section gives concrete context (edit a record; advance a deal with {stage}; complete a task with {status:'done'}). It references the lead-conversion guide rather than giving explicit when-not-to-use or naming a competing sibling edit tool, so it falls just short of a 5.

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