Skip to main content
Glama

push_artifact

Write edited artifact fields back to ServiceNow records, using expected_updated_on to abort on conflicts and optionally loading field values from local sync files.

Instructions

Local sync: write edited fields back to an artifact (requires WRITE_ENABLED=true). Pass fields inline as {field:value}; if omitted and NOWAIKIT_SYNC_DIR is set, reads them from the pulled files on disk. Overwrites the listed fields with NO merge — run sync_status first, and pass expected_updated_on to abort if the instance changed since you pulled.

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": {
      "table": "<table>",
      "sys_id": "<sys_id>"
    },
    "name": "push_artifact"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYesArtifact table
fieldsNoOptional map of {field: newValue} to update; defaults to the on-disk files under NOWAIKIT_SYNC_DIR
sys_idYessys_id OR name of the record
expected_updated_onNoOptional sys_updated_on from your last pull/sync_status; the push aborts with a CONFLICT if the record has changed since.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.9.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes well past the annotations by disclosing the no-merge overwrite semantics, the env-var-gated disk fallback (NOWAIKIT_SYNC_DIR), and the optimistic-concurrency abort behavior via expected_updated_on. Annotations only flag readOnly=false and idempotent=false; the description supplies the operational consequences.

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?

Three densely packed sentences, front-loaded with the core action and prerequisites. Every clause carries information; it is tight, though the density (env vars, fallback logic, conflict semantics) makes it slightly heavy for a single paragraph.

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?

With no output schema, the description still covers the write scope, failure path, and input sourcing needed to call it correctly. It stops short of describing what the tool returns on success, which is the remaining gap.

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%, but the description still adds meaning: the inline {field:value} format for fields, the conditional disk-sourcing behavior when fields is omitted, and that sys_id accepts either an id or a name. These are the decision-relevant behaviors an agent needs at call time.

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?

States a specific verb and resource ("write edited fields back to an artifact") and frames it as a local sync operation, which distinguishes it from the sibling pull_artifact/sync_status. It does not name an alternative beyond sync_status as a prerequisite, so it falls just short of full sibling differentiation.

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 preconditions (WRITE_ENABLED=true, run sync_status first, pass expected_updated_on) and spells out the failure mode (abort with CONFLICT if the record changed). The agent knows both when to call it and what to do beforehand.

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

Deploy Server

Other Tools