Skip to main content
Glama
Sign In

Spaces by Peakflo

by ai.peakflo
OverviewDiscussionsAdmin

task_update

Destructive

Update a human task's metadata (title, description, priority, due date, status, assignees).

Only open tasks can be updated (status not_started, triaging, agent_working or ready_for_review). To complete a task, use task_complete instead.

Parameters:

  • taskId: The task ID to update (required)

  • title: New task title

  • description: New description (empty string to clear)

  • priority: low, medium, high, or urgent

  • dueDate: ISO 8601 date (empty string to clear)

  • expiresAt: ISO 8601 date (empty string to clear)

  • status: pending or in_progress

  • assignees: JSON string of assignees array, e.g. [{"assigneeType":"user","assigneeValue":""}]

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": {
      "taskId": "<taskId>"
    },
    "name": "task_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoNew task title
statusNoNew status: pending or in_progress (use task_complete to complete tasks)
taskIdYesThe task ID to update
dueDateNoNew due date in ISO 8601 format (set to empty string to clear)
priorityNoNew priority: low, medium, high, urgent
assigneesNoJSON string of assignees array to replace the current assignees. Each element: { "assigneeType": "user"|"email", "assigneeValue": "<userId or email>" }
expiresAtNoNew expiration date in ISO 8601 format (set to empty string to clear)
descriptionNoNew task description (set to empty string to clear)

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 readOnlyHint=false and destructiveHint=true, and the description supplies the operative constraint that only non-terminal tasks accept edits, plus the empty-string-to-clear semantics for description/dueDate/expiresAt. It does not explain that assignees are wholesale replaced rather than merged, nor what the response contains, but with annotations carrying the safety profile a 4 is fair.

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

Conciseness3/5

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

The rule and the alternative are front-loaded well, which is correct ordering. But the eight-item parameter block duplicates schema text verbatim at 100% coverage, spending several lines on information the agent already has while the genuine ambiguity around status values goes unresolved.

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 destructive, schema-rich mutation tool with no output schema, the description covers the necessary ground: scope of mutable fields, the open-task precondition, the sibling to use instead, and clearing semantics. The remaining weakness is the unresolved mismatch between the listed task states and the accepted status values, which is the one thing an agent is most likely to get wrong.

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 description coverage is 100%, so the schema already documents all eight parameters and the description's parameter list largely restates them. The one piece of added meaning, the clearing convention via empty string, is also present in the schema, and the status value set given here contradicts the status set named in the preceding paragraph, which is the opposite of added clarity.

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 opening sentence names a specific verb and resource ('Update a human task's metadata') and enumerates the mutable fields, so the agent knows exactly what class of operation this is. The follow-up sentence distinguishes it from the sibling task_complete, which handles completion rather than metadata edits.

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?

It gives an explicit precondition ('Only open tasks can be updated') and names the correct alternative ('To complete a task, use task_complete instead'), which is strong when-to-use guidance. However, the allowed-task-status list (not_started, triaging, agent_working, ready_for_review) directly conflicts with the status values offered for the status parameter (pending, in_progress), leaving the agent unsure which vocabulary actually gates a valid update.

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

All Spaces by Peakflo toolsInspect
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