Skip to main content
Glama

Create Mass Update Run

create_mass_update_run

Create a run that sets named fields to declared values across a scoped population, and/or applies Segments whose labels are written to a target field. Requires at least one of assignment_spec (which fields get which values) or segment_spec. Every record in scope gets the same change, which is what separates this from enrichment. TO SET AN OWNER, assign owner_id a literal user id from list_crm_users. That is a ONE-TIME correction and leaves no policy behind: records created later are unaffected, and nothing records why these records have that owner. Ongoing ownership by territory or any other rule is what an assignment run does instead, from configuration a person authors -- see get_assignment_config. TO DELETE RECORDS, set delete=true with a filter_spec and nothing else: contacts, leads or accounts on Salesforce; contacts or companies (object_type account) on HubSpot, which has no leads. A person always decides a delete. disposition 'propose' (the default for a delete) puts one proposal per record in the review queue, each approved by a person; 'queue' holds the run until a person approves it, which then deletes every record in scope; 'execute' is refused, and so is a delete with no filter_spec. ON SALESFORCE an account goes with its contacts, opportunities and cases, which each account's proposal counts, and every delete moves the record to the Recycle Bin and can be undone for 15 days. ON HUBSPOT a company's contacts and deals are not deleted, only unlinked; every delete moves the record to HubSpot's recycle bin, and undoing it recreates the record from LiveCRM's snapshot under a new id and links it back. Undo from the CRM write log or by reversing the run.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesA name for the run, shown in the Runs tab. Every record in scope gets the same change.
deleteNoDelete the records in scope instead of changing their fields. On Salesforce: contacts, leads and accounts; an account goes with its contacts, opportunities and cases, which each account's proposal counts, and each delete moves the record to the Recycle Bin and can be undone for 15 days. On HubSpot: contacts and companies (account); a company's contacts and deals are NOT deleted, only unlinked, and each delete moves the record to HubSpot's recycle bin, where an undo recreates it from LiveCRM's snapshot under a new id. The run carries a scope (required) and nothing else. A person always decides: 'propose' (the default) puts one proposal per record in the review queue, approved one at a time; 'queue' waits for a person to approve the run, which then deletes every record in scope; 'execute' is refused.
score_specNoScores to publish to CRM fields. The value comes from an earlier score run; a record that run has not scored is skipped, not scored here.
dispositionNoWho releases this run's writes. 'execute' dispatches the pass on request, which is the default and what every run has always done. 'queue' stamps the run awaiting_approval and launches nothing until a person approves it. 'propose' dispatches the pass, which computes everything and writes NOTHING to the CRM, putting one reviewable proposal in the queue per record it would have changed — so a person approves the changes one at a time instead of the run wholesale. A credential may ask for either form of review and may never release it. Note that 'propose' still SPENDS what computing spends: an enrichment set to propose buys the provider data and then queues the writes, because a value nobody fetched cannot be proposed.execute
filter_specNoWhich records this run covers, as a filter tree. Omit for the whole object. It DESCRIBES a population and is resolved when the run is DISPATCHED, so write what you mean -- the CRO at Skypoint is `account_name is Skypoint AND title contains CRO` -- and never look a record up to write one. You need no ids and no counts. Call list_filterable_fields first, for the field names and operators only.
object_typeYesWhich CRM object the run targets: contact, account or lead.
segment_specNoSegments to apply, each with the CRM field its label is written to. The same shape as create_segmentation_run's segment_spec.
connection_idYesThe CRM connection. Required. Call list_crm_connections to get one.
assignment_specNoField values to set: the object and a list of field assignments, all written in one pass. A run needs at least one of assignment_spec, segment_spec or score_spec, unless delete is true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / assignment_spec / description
      Added value: +"Field values to set: the object and a list of field assignments, all written in one pass. A run needs at least one of assignment_spec, segment_spec or score_spec, unless delete is true."
    • addedInput schema / properties / score_spec / description
      Added value: +"Scores to publish to CRM fields. The value comes from an earlier score run; a record that run has not scored is skipped, not scored here."
    • addedInput schema / properties / segment_spec / description
      Added value: +"Segments to apply, each with the CRM field its label is written to. The same shape as create_segmentation_run's segment_spec."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Far exceeds the annotations: it discloses per-platform delete semantics (Salesforce cascade + Recycle Bin with 15-day undo; HubSpot unlink-not-delete + snapshot recreation under a new id), the human-approval requirement ('execute' is refused for deletes), and the side effect that 'propose' still spends enrichment budget. Annotations only say readOnlyHint=false/destructiveHint=false; the description carries all the operational detail.

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-loads the core purpose and the required-spec rule before the long operational caveats, and the ALL-CAPS signposting aids scanning. It is verbose and the delete paragraph largely duplicates the schema's own delete description, so it is not maximally tight, but given the tool's complexity most sentences earn their place.

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 9-parameter, high-stakes tool with no output schema, it covers scope, alternatives, approval gates, and cross-platform differences thoroughly. The only gap is that it never states what the call returns (e.g. a run id for later dispatch/approval), which the agent must infer.

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 schema already documents each parameter and its baseline is 3. The description adds genuinely useful meaning beyond the schema — owner_id must be a literal id from list_crm_users, delete must pair with a filter_spec and nothing else, and the propose/queue/execute dispositions — though it also restates much of the delete parameter's own schema text.

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?

Opens with a specific verb+resource ('Create a run that sets named fields to declared values across a scoped population, and/or applies Segments') and explicitly distinguishes itself from enrichment ('Every record in scope gets the same change, which is what separates this from enrichment'). An agent can identify the tool's scope and its boundaries with siblings 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use/when-not-to guidance: owner_id is a ONE-TIME correction vs. rule-based ownership via get_assignment_config; delete requires delete=true with filter_spec and nothing else; and it names concrete alternatives (list_crm_users, get_assignment_config, list_filterable_fields). The condition selecting each path is spelled out.

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.