Skip to main content
Glama

AssetLab

Update work order

update_work_order
DestructiveIdempotent

Update an existing work order by ID. Requires work_orders:write scope. When changing location, resolve top-down: list_sites → list_buildings (by site_id) → list_locations (by building_id). Provide all three IDs. To complete a work order, set status COMPLETED and say what was done in completion_notes; completed_at is stamped automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesWork order ID
typeNoWork order type
titleNoWork order title
statusNoStatus
site_idNoSite ID - resolve first via list_sites
asset_idNoAsset this work order is for - resolve via list_assets. The server mirrors it into asset_ids.
due_dateNoDue date (ISO 8601)
priorityNoPriority level
asset_idsNoAssets this work order covers - use instead of asset_id when there is more than one.
assigneesNoArray of assigned user IDs (alternative to assigned_to for multiple assignees)
image_urlNoImage storage path (upload via create_upload_url with bucket "attachments", then set this to the returned path)
meter_unitNoMeter unit (km, miles, hours, cycles)
start_dateNoStart date (ISO 8601)
system_idsNoSystems this work order covers - resolve via list_systems. Systems have no singular field; this array is the only way to associate them.
assigned_toNoAssigned user ID (mapped to assignees array)
building_idNoBuilding ID - resolve second via list_buildings filtered by site_id
descriptionNoDetailed description
location_idNoLocation this work order is for - resolve last via list_locations filtered by building_id. The server mirrors it into location_ids, so send this OR location_ids, not a conflicting pair.
location_idsNoLocations this work order covers - use instead of location_id when there is more than one. Sending location_id alone replaces this with that single id.
meter_readingNoMeter/odometer reading at time of service
estimated_costNoEstimated cost
estimated_timeNoEstimated time in hours
completion_notesNoWhat was done, recorded on the work order when it is completed
work_category_idNoWork category ID
purchase_order_idNoPurchase order that paid this work order's actual cost - resolve via list_purchase_orders. Counts against the order's remaining balance; null clears it.
infrastructure_asset_idsNoInfrastructure features this work order covers - resolve via list_infrastructure_assets. Use this when one job covers several features (a round of hydrant flushing); the whole selection is one work order with one completion and one cost, split across the features. Mutually exclusive with asset/location/system targets.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint, idempotentHint and openWorldHint=false. The description adds value beyond them: the required work_orders:write scope, the fact that completed_at is stamped automatically, and the multi-step location resolution requirement. It does not clarify what a destructive update actually overwrites, but the auth and side-effect disclosures are meaningful.

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 front-loaded sentences with essentially no filler; the core action comes first, then the location workflow, then the completion workflow. Densest tool in the family but every sentence carries actionable information.

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 26-parameter mutation with no output schema, the description covers the highest-risk workflows (location changes, completion) and the auth requirement. It leaves the asset_id/asset_ids and location_id/location_ids mirroring behavior to the schema, which documents those thoroughly, so the overall picture is complete enough to invoke correctly.

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 cross-field semantics the schema cannot convey: the ordered top-down resolution for the three location IDs, the required all-three-IDs constraint, and the status/completion_notes coupling. This is genuine added meaning over the schema.

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 with the identifying key ("Update an existing work order by ID"), which is unambiguous. It does not explicitly distinguish itself from the closest siblings bulk_update or update_work_order_schedule, but the singular 'by ID' framing implies this. Clear but not sibling-differentiated.

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?

Provides concrete when-to-use workflow guidance for two specific cases: changing location (resolve top-down through list_sites → list_buildings → list_locations) and completing a work order (set COMPLETED + completion_notes). No explicit exclusions or alternatives named (e.g. vs bulk_update), but the conditional guidance is strong.

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