Skip to main content
Glama

BoardMark

by ai.boardmark
OverviewDiscussionsAdmin

Remove a link

unlink_issues
DestructiveIdempotent

Remove a link.

version is the version of THIS issue (from get_issue). target is the linked issue's key as stored in frontmatter.links — of this or another project of the company; the inverse link in the other project is removed too. For link_type: delivers the target is the release KEY/R-n exactly as stored in frontmatter.links (NW/R-1); no inverse exists to remove. Pass KEY/R-n as is — the slash is encoded for you.

WRITE: version = from your latest read (get_issue, list_comments, list_sprints, get_doc, read_file). 409 version_conflict (details.current, details.current_version): re-read, re-apply your change, retry — never overwrite blindly; when the changes disagree, ask the user.

Input Schema

NameRequiredDescriptionDefault
reasonNoSpec D144: why you make this change (≤ 200 characters). Optional, but give it when you act as an agent account — it is shown in the agent's run log. board-mcp records it; the service accepts and ignores it.
targetYesThe linked issue key, or for type `delivers` the release `KEY/R-n` (send it URL-encoded: `KEY%2FR-n`).
versionYesVersion of the file you read. Required on every delete (spec principle 7).
issue_keyYesIssue key `{PROJECT}-{n}`, e.g. `KJ-101`.
link_typeYesLink types, stored on the source issue. board-core keeps the inverse on the target in step: blocks↔blocked_by, duplicates↔duplicated_by, clones↔cloned_by, relates↔relates. `delivers` (D131 (1)) points at a release (`id` = releaseRef `KEY/R-n`, same company) — the goal or deal is delivered by that release; no inverse is written (releases are not issues).
project_keyYesProject key, e.g. `KJ`. 2–10 chars, uppercase letters and digits, starts with a letter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / reason
      Added value: +{
+  "description": "Spec D144: why you make this change (≤ 200 characters). Optional, but give it when you act as an agent account — it is shown in the agent's run log. board-mcp records it; the service accepts and ignores it.",
+  "maxLength": 200,
+  "type": "string"
+}
    • changedInput schema / properties / target / description
      Previous value: -"Issue key `{PROJECT}-{n}`, e.g. `KJ-101`."New value: +"The linked issue key, or for type `delivers` the release `KEY/R-n` (send it URL-encoded: `KEY%2FR-n`)."
    • changedInput schema / properties / target / pattern
      Previous value: -"^[A-Z][A-Z0-9]{1,9}-[1-9][0-9]*$"New value: +"(?:^[A-Z][A-Z0-9]{1,9}-[1-9][0-9]*$)|(?:^[A-Z][A-Z0-9]{1,9}/R-[1-9][0-9]*$)"
  2. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description goes further by disclosing the cross-project side effect — the inverse link in the other project is removed too — and the exception that `delivers` links write no inverse because releases are not issues. It also specifies the conflict-recovery protocol (409 details.current, re-read before retry, never overwrite blindly), which annotations cannot express.

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?

Purpose leads, the two non-obvious parameter semantics follow, and the write/conflict contract closes. The final paragraph is partly generic boilerplate about version conflicts, but every sentence carries operational content; nothing is padding.

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 6 parameters, no output schema and destructive semantics, the description covers the side effects, the release special case, and the concurrent-write recovery path. Gaps remain minor: it does not say what happens when no such link exists (error vs no-op), nor why `reason` should be supplied; the encoding disagreement with the schema also leaves a small ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the property descriptions already explain project_key, issue_key, target and version, so the baseline is 3. The description does add real meaning — `version` is of THIS issue, `target` is stored in `frontmatter.links`, `delivers` targets a release ref — but it also conflicts with the schema on encoding ('pass as is — the slash is encoded for you' versus 'send it URL-encoded: KEY%2FR-n'), leaving the agent unsure which form the pattern expects.

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?

The opening 'Remove a link' pairs a specific verb with a specific resource, and the target/link_type discussion makes clear it operates on issue-to-issue (and issue-to-release) link records. It never names the counterpart tool link_issues, so the agent must infer the inverse pairing from the sibling list rather than being told.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated: nothing says when to unlink versus edit a link, or that changing a link type means unlink-then-link. What guidance exists is operational (version must come from your latest read; on 409 re-read, re-apply, retry, ask the user when changes disagree), which is valuable but is about how to call, not when to choose this tool over alternatives.

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

All BoardMark toolsInspect
Try in Browser
Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources