Skip to main content
Glama

delete_work_item_links

DestructiveIdempotent

Delete up to 50 outgoing links from a source work item in Polarion. Specify each link by role and target work item; stale references are reported instead of failing.

Instructions

Delete 1-50 outgoing links from one source work item.

Outgoing only — delete a back link from its source item instead. Refs from list_work_item_links(direction="forward") or a prior create. Stale refs never fail: results split into deleted_link_ids / not_found_link_ids.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
linksYesExisting outgoing links to delete (1-50).
dry_runNoPreview payload without deleting; the pre-read still queries Polarion.
project_idYesSource work item's project ID.
work_item_idYesSource work item ID.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
deletedYes
dry_runYes
link_idsNo
payload_previewNo
deleted_link_idsNo
not_found_link_idsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0
  2. Removedv2.0.0
  3. Changed1 schema field changedv1.4.1
    • addedInput schema / properties / links / items / additionalProperties
      Added value: +false
  4. Changed3 schema fields changedv1.4.0
    • changedInput schema / properties / dry_run / description
      Previous value: -"When True, return payload preview without calling Polarion."New value: +"Preview payload without deleting; the pre-read still queries Polarion."
    • changedInput schema / properties / links / description
      Previous value: -"One or more existing outgoing links to delete (1-50)."New value: +"Existing outgoing links to delete (1-50)."
    • changedInput schema / properties / work_item_id / description
      Previous value: -"Source work item ID (the links' outgoing endpoint)."New value: +"Source work item ID."
  5. Changed14 schema fields changedv1.1.0
    • changedInput schema / properties / links / description
      Previous value: -"One or more existing outgoing links to delete."New value: +"One or more existing outgoing links to delete (1-50)."
    • removedInput schema / properties / links / items / properties / role / description
      Removed value: -"Link role id; must match exactly."
    • removedInput schema / properties / links / items / properties / target_project_id / description
      Removed value: -"Target's project; defaults to the source's project."
    • removedInput schema / properties / links / items / properties / target_work_item_id / description
      Removed value: -"Target work item ID."
    • addedInput schema / properties / links / maxItems
      Added value: +50
    • removedOutput schema / $defs
      Removed value: -{
      -  "JsonValue": {
      -    "anyOf": [
      -      {
      -        "type": "string"
      -      },
      -      {
      -        "type": "integer"
      -      },
      -      {
      -        "type": "number"
      -      },
      -      {
      -        "type": "boolean"
      -      },
      -      {
      -        "items": {
      -          "$ref": "#/$defs/JsonValue"
      -        },
      -        "type": "array"
      -      },
      -      {
      -        "additionalProperties": {
      -          "$ref": "#/$defs/JsonValue"
      -        },
      -        "type": "object"
      -      },
      -      {
      -        "type": "null"
      -      }
      -    ]
      -  }
      -}
    • changedOutput schema / description
      Previous value: -"Result of a ``delete_work_item_links`` operation.\n\n``link_ids`` echoes the REQUEST — Polarion silently ignores body-level\nrefs that do not match an existing link, so the echo is not a list of\nwhat was actually deleted. Cross-check with ``list_work_item_links``\nif exact accounting is required."New value: +"Result of a ``delete_work_item_links`` operation."
    • removedOutput schema / properties / deleted / description
      Removed value: -"True on a real delete; False on dry-run."
    • addedOutput schema / properties / deleted_link_ids
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedOutput schema / properties / dry_run / description
      Removed value: -"Whether this was a dry-run."
    • removedOutput schema / properties / link_ids / description
      Removed value: -"Composite 5-segment ids reconstructed from the request refs."
    • addedOutput schema / properties / not_found_link_ids
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / payload_preview / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": {
      -      "$ref": "#/$defs/JsonValue"
      -    },
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": true,
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / payload_preview / description
      Removed value: -"JSON:API payload sent or previewed; None after real ops."
  6. First observedv0.9.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true. The description adds valuable behavioral details: stale refs never fail, results split into deleted/not_found, and mentions dry_run feature. No contradiction with annotations.

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

Conciseness5/5

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

The description is highly concise: two short paragraphs with no wasted words. The main action and limit are front-loaded, and essential usage notes follow immediately. Every sentence earns its 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?

Given the tool's destructive nature and 4 parameters, the description covers behavior for stale refs, dry run, and directionality. An output schema exists, so return values are not needed. A minor gap is the lack of explicit prerequisites or permissions, but overall it is sufficiently complete.

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 adds meaning beyond the schema by clarifying that the 'links' parameter should contain existing outgoing links (obtained from list_work_item_links) and that stale refs are handled gracefully. This enriches the agent's understanding.

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?

The description clearly states the action (delete), resource (outgoing links from a source work item), and scope (1-50 links). It effectively distinguishes from sibling tools like list_work_item_links and update_work_item_link by specifying 'outgoing only'.

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?

The description explicitly states when to use (for outgoing links) and when not (for back links, use the source item). It references list_work_item_links for obtaining link IDs and explains behavior with stale refs, providing clear context for correct usage.

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