Skip to main content
Glama

TaScan

by io.github.snowbikemike
OverviewDiscussionsAdmin

tascan_update_task

Idempotent

Update a task (title, description, response_type, flags, sort_order). A task that sits in an AI agent inbox is agent input (the runner executes title + description), so ANY edit to it needs the agent:dispatch permission — agent:dispatch:code when the task is or becomes CODE:/SHELL:.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleNoNew title
task_idYesTask ID
sort_orderNoSort position
assigned_toNoWorker to assign this task to — pass the worker UUID (validated against your org and stored as the worker's name, which is how the worker portal matches "my tasks"). A plain name string is also accepted as-is. Pass null to clear.
descriptionNoNew description
response_typeNoSee tascan_add_tasks for guidance. "text" for info collection, "photo" for visual proof, "checkbox" for yes/no only, "link" for the worker submitting a URL, "url" for the worker visiting a preset URL and confirming, "file" for the worker uploading a file.
requires_photoNoRequire photo
response_configNoResponse configuration. For "choice": {options: [...]}. See tascan_add_tasks.
required_equipmentNoEquipment this task depends on (free text)
is_safety_checkpointNoSafety-critical flag

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / response_type / description
      Previous value: -"See tascan_add_tasks for guidance. \"text\" for info collection, \"photo\" for visual proof, \"checkbox\" for yes/no only."New value: +"See tascan_add_tasks for guidance. \"text\" for info collection, \"photo\" for visual proof, \"checkbox\" for yes/no only, \"link\" for the worker submitting a URL, \"url\" for the worker visiting a preset URL and confirming, \"file\" for the worker uploading a file."
    • changedInput schema / properties / response_type / enum
      Previous value: -[
-  "checkbox",
-  "photo",
-  "text",
-  "number",
-  "date",
-  "choice"
-]New value: +[
+  "checkbox",
+  "photo",
+  "text",
+  "number",
+  "date",
+  "choice",
+  "link",
+  "url",
+  "file"
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / assigned_to
      Added value: +{
+  "description": "Worker to assign this task to — pass the worker UUID (validated against your org and stored as the worker's name, which is how the worker portal matches \"my tasks\"). A plain name string is also accepted as-is. Pass null to clear.",
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • addedInput schema / properties / required_equipment
      Added value: +{
+  "description": "Equipment this task depends on (free text)",
+  "type": "string"
+}
    • addedInput schema / properties / response_config
      Added value: +{
+  "description": "Response configuration. For \"choice\": {options: [...]}. See tascan_add_tasks.",
+  "type": "object"
+}
  4. Changed1 schema field changed
    • changedInput schema / properties / response_type / description
      Previous value: -"Task type"New value: +"See tascan_add_tasks for guidance. \"text\" for info collection, \"photo\" for visual proof, \"checkbox\" for yes/no only."
  5. First observed

TDQS

A3.6/5.0
Behavior4/5

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

The description goes beyond the annotations by explaining that an agent-inbox task's title and description are executed by a runner and that any edit requires agent:dispatch permissions, with a special code-level permission for CODE:/SHELL: tasks. This adds meaningful behavioral context that annotations do not cover, and there is no contradiction with the idempotentHint=true or destructiveHint=false annotations.

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?

The description is compact and front-loaded with the core action and fields, and it packs the crucial permission context into the second sentence. The inclusion of 'flags' is a minor accuracy issue, but overall the text is efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 10 parameters and nested objects, the description provides essential permission context but does not describe return values, error behavior, or the effect of unmentioned fields. It is adequate for basic selection and invocation, but not fully complete for an agent executing this tool in edge cases.

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 parameters. The description lists some editable fields but does not add meaningful semantics beyond the schema, and it references 'flags,' which is not a parameter in the schema, slightly reducing the value of its parameter guidance.

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 description names a clear verb and resource ('Update a task') and lists several editable fields, which distinguishes it from sibling tools like tascan_delete_task and tascan_update_subtask. However, it references 'flags' even though no such parameter exists in the input schema, and it omits other updatable fields like assigned_to, so the purpose is clear but slightly imprecise.

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?

The description provides important context about when extra permission is required, specifically for tasks sitting in an AI agent inbox, and explains the code-related permission variant. It does not name alternatives or explicitly state when to prefer a different tool, so usage guidance is present but not fully developed.

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

All TaScan 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