Skip to main content
Glama
ihorponom

agentpack

by ihorponom
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

task_switch

Destructive

Switch the current Task Passport to another open task by ID, optionally parking the active one in the same locked transaction.

Instructions

Make another open Task Passport current by id. Set parkCurrent: true to park a different active/blocked/verifying current task in the same locked transaction, after validating the target. Otherwise park or finalize it first. A parked target with pending or unknown verification resumes as active; a parked target with a final verdict resumes as verifying and stays frozen until verification returns to pending. Closed targets cannot be switched to.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesTask Passport id to switch to (see task_list).
parkCurrentNoPark a different current open task and switch in one call. Default false; preserves its verification and bound HEAD.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.8
    • addedInput schema / properties / parkCurrent
      Added value: +{
+  "description": "Park a different current open task and switch in one call. Default false; preserves its verification and bound HEAD.",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv1.4.0
    • addedInput schema / properties / id / description
      Added value: +"Task Passport id to switch to (see task_list)."
  3. First observedv1.3.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations (which only state destructive/non-idempotent/non-readonly). It discloses the transactional boundary ('same locked transaction, after validating the target') and the full verification state machine: a parked target with pending/unknown verification resumes as active, one with a final verdict resumes as verifying and stays frozen until verification returns to pending.

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?

Front-loaded with the core action, then the parkCurrent behavior, then edge cases. Dense but every sentence carries behavioral information; the verification-state sentence is heavy but necessary for correct invocation.

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, non-idempotent mutation with 2 params and no output schema, it covers prerequisites, atomicity, and target-state rules. It omits error/conflict handling beyond 'closed targets cannot be switched to' and any indication of what the call returns, which slightly limits completeness.

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%, so the baseline is 3. The description adds meaning beyond the schema by specifying which current states parkCurrent can handle (active/blocked/verifying) and that parking preserves verification and bound HEAD, which the schema description does not state.

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?

States a specific verb and resource: it switches the current 'open Task Passport' to another by id. This clearly differentiates it from siblings like task_park and task_finalize, which it explicitly references. The 'Task Passport' terminology is domain jargon, but the action is unambiguous.

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?

Gives real routing guidance: use parkCurrent:true to switch in one atomic call, otherwise park or finalize the current task first, and closed targets cannot be switched to. It does not name sibling alternatives by name (task_park/task_finalize are only implied), but the when/when-not conditions are explicit.

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

Deploy Server

Other Tools