Skip to main content
Glama
Sign In
Polarion MCP Server

Polarion MCP Server

by phillipboesger
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

patchCustomField

DestructiveIdempotent

Replace a project's complete custom-field list for a resource and target type; omitted fields are deleted, not merged. Preview with dry_run first because changes are irreversible.

Instructions

Replaces the entire list of Custom Fields of one project for one resource type and target type: fields missing from requestBody are deleted, not merged. Read the current list with getProjectCustomFields first and send every field you want to keep. Effect: irreversible — data removed or overwritten by this call cannot be recovered through the API. Tip: set dry_run: true first to validate the arguments and preview the exact request without sending it to Polarion. The executor returns this preview as normal text, and as structured content when the tool declares an output schema.

Input Schema

NameRequiredDescriptionDefault
dry_runNoIf true, validates the request and returns the exact request that would be sent to Polarion — with the Authorization header redacted and any binary payload summarized by byte length — without actually sending it.
projectIdYesThe Polarion project ID (its URL segment, e.g. `myproject`), case-sensitive. Required to scope the request to one project. If the ID is unknown, ask the user; getProjects lists IDs only with global read access.
targetTypeYesThe configured subtype for this enumeration or custom field (e.g. `requirement` for a Work Item type). Use `~` (without quotes) when the configuration applies to every subtype.
requestBodyYesCustom Fields Body
resourceTypeYesThe Resource Type.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.4
    • changedInput schema / properties / projectId / description
      Previous value: -"The Polarion project ID (its URL segment, e.g. `myproject`), case-sensitive. Required to scope the request to one project; call getProjects to list valid IDs."New value: +"The Polarion project ID (its URL segment, e.g. `myproject`), case-sensitive. Required to scope the request to one project. If the ID is unknown, ask the user; getProjects lists IDs only with global read access."
  2. Changed1 schema field changedv1.4.0
    • changedInput schema / properties / targetType / description
      Previous value: -"Identifies the target resource type this operation applies to (e.g. `workitem`). Use `~` (no quotes) to mean no specific target type."New value: +"The configured subtype for this enumeration or custom field (e.g. `requirement` for a Work Item type). Use `~` (without quotes) when the configuration applies to every subtype."
  3. Changed3 schema fields changedv1.2.0
    • changedInput schema / properties / dry_run / description
      Previous value: -"If true, validate and return the request that would be sent without calling Polarion."New value: +"If true, validates the request and returns the exact request that would be sent to Polarion — with the Authorization header redacted and any binary payload summarized by byte length — without actually sending it."
    • changedInput schema / properties / projectId / description
      Previous value: -"The Project ID."New value: +"The Polarion project ID (its URL segment, e.g. `myproject`), case-sensitive. Required to scope the request to one project; call getProjects to list valid IDs."
    • changedInput schema / properties / targetType / description
      Previous value: -"The Custom Field target type. (Use '~' when there is no specific type for the Prototype.)"New value: +"Identifies the target resource type this operation applies to (e.g. `workitem`). Use `~` (no quotes) to mean no specific target type."
  4. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, but the description goes further by explaining the exact destruction mechanism (fields missing from `requestBody` are deleted, not merged), the irreversibility of that loss, and the dry-run escape hatch. This is precisely the context annotations cannot convey.

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 destructive replace semantic, then remedy, then tip — a good ordering with almost no filler. The closing sentence about structured content only when an output schema is declared is slightly meta and marginally wasteful given no output schema exists here.

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?

For a destructive, nested-body mutation with no output schema, the description covers what is replaced, what is lost, how to preview safely, and which read tool supplies the input. Nothing an agent needs in order to call this correctly is missing.

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. The description still adds real value by defining the replace-not-merge semantics of `requestBody` and the preview behavior of `dry_run`, which no schema field description states. It stops short of explaining resourceType/targetType combinations beyond the 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?

States a specific verb and resource with exact scope: 'Replaces the entire list of Custom Fields of one project for one resource type and target type.' This distinguishes it from postProjectCustomFields, patchGlobalCustomFields, and deleteProjectCustomFields without the agent needing to open any 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 prerequisites: read the current list with `getProjectCustomFields` first and send every field to keep, and optionally set `dry_run: true` to validate. It names the sibling to read from and the condition that selects it, leaving nothing to inference.

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