mcptask.online

UpdatePieceTool

Destructive

Update the mutable attributes of an existing Task, Story, Epic or Recurent by relative_id. Only the attributes passed are changed; omitted ones are left alone. Returns before/after for each attribute touched. A dependency on another piece is declared with blocked_by_relative_ids — the updated piece waits for the ids listed there.

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": {
      "account_code": "<account_code>",
      "piece_relative_id": "<piece_relative_id>"
    },
    "name": "UpdatePieceTool"
  }
}

Input Schema

Name	Required	Description
`name`	No	New name for the piece (omit to leave unchanged)
`repeat_on`	No	One value: monday–friday for 1week/2weeks, a day of the month "1"–"31" for 1month. Omit to leave unchanged.
`sprint_id`	No	Database ID (primary key) of the sprint to assign (not relative_id). Omit to leave unchanged.
`for_errors`	No	Whether this Epic is the project's bug bucket (Epic only). Omit to leave unchanged. Passing it for another piece type returns a validation error.
`description`	No	New description for the piece (omit to leave unchanged)
`account_code`	Yes	Account code (e.g., "bcp", "jchsoft")
`repeat_after`	No	Repeat a Task every 1week, 2weeks or 1month; only a Task inside an Epic or a Recurent repeats; needs repeat_on. Omit to leave unchanged; pass null (with repeat_on null or omitted) to end the repetition.
`priority_code`	No	Priority code. Omit to leave unchanged.
`task_type_code`	No	Task type code (Task only). Omit to leave unchanged.
`assigned_user_id`	No	Database ID (primary key) of the user to assign. Omit to leave unchanged; pass 0 (or null) to explicitly unassign.
`scrum_point_code`	No	Scrum point/complexity code (Task/Recurent: !, S, M, L, XL, XXL, XXXL; Story: m!, mS, mM, mL, mXL, mXXL, mXXXL). Omit to leave unchanged.
`piece_relative_id`	Yes	Relative ID of the piece to update
`parent_relative_id`	No	Relative ID of a parent piece in the same project. Omit to leave unchanged; pass 0 (or null) to move the piece to the project root.
`blocked_by_relative_ids`	No	Relative IDs of the pieces this piece waits for (its blocked_by links). Additive: it only adds links — remove them with ManageBlockerLinksTool(action: "remove"); an id already linked is refused, do not re-send it. All-or-nothing: one id that does not resolve in the account rejects the whole call and creates nothing.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 12, 2026

addedInput schema / properties / repeat_after

Added value: +{
+  "description": "Repeat a Task every 1week, 2weeks or 1month; only a Task inside an Epic or a Recurent repeats; needs repeat_on. Omit to leave unchanged; pass null (with repeat_on null or omitted) to end the repetition.",
+  "enum": [
+    "1week",
+    "2weeks",
+    "1month"
+  ],
+  "type": [
+    "null",
+    "string"
+  ]
+}

addedInput schema / properties / repeat_on

Added value: +{
+  "description": "One value: monday–friday for 1week/2weeks, a day of the month \"1\"–\"31\" for 1month. Omit to leave unchanged.",
+  "type": [
+    "null",
+    "string"
+  ]
+}

First observedSep 14, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known; the description adds real value on top by disclosing patch semantics (omitted attributes untouched) and the return shape ("before/after for each attribute touched"). The blocked_by note explains additive-only and all-or-nothing rejection, which an agent could not infer from annotations, though nothing is said about permission requirements or how to recover a partially successful update.

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?

Four short sentences, front-loaded with purpose before contract, return value and the one non-obvious parameter caveat. Nothing is redundant with the annotations and no sentence 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?

For a 14-parameter destructive mutation with no output schema, the description covers the essential contract: patch semantics, return shape, and the risky blocked_by side effect. It falls slightly short on what "mutable" excludes and on any permission or error-recovery context an agent would want before a destructive call.

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%, so every parameter already carries its own description, including the per-parameter "omit to leave unchanged" contract and the blocked_by additivity warning. The prose adds the useful framing that attributes are "mutable" (some are not settable here) and restates the dependency semantics, but beyond that it duplicates the schema rather than adding syntax or edge-case meaning.

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?

"Update the mutable attributes of an existing Task, Story, Epic or Recurent by relative_id" gives a specific verb, names the piece types it applies to, and states the identifier convention. It also explicitly contrasts with ManageBlockerLinksTool (removing links) so an agent can tell where this tool's remit ends.

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: "existing" implies not for creation, and the patch contract ("only the attributes passed are changed") tells the agent how to call it. The only explicit routing is toward ManageBlockerLinksTool for link removal; there is no statement telling the agent to use CreatePieceTool for new pieces or when to stop passing an attribute instead of updating.

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

All mcptask.online tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?