Skip to main content
Glama

TaScan

by io.github.snowbikemike
OverviewDiscussionsAdmin

tascan_dispatch_to_agent

PREFERRED tool for sending work to an AI agent. Dispatches a task to the agent's inbox — picked up and executed automatically. No list ID needed. REQUIRES the agent:dispatch permission on this connection (CODE:/SHELL: tasks also require agent:dispatch:code) — reconnect and tick the agent checkbox(es) if refused. Routing is by TITLE PREFIX only: CODE: SHELL: PLAN: MCP: → local Claude Code on Mike's PC; RESEARCH: WRITE: REVIEW: → cloud; no prefix (DEFAULT) → local while the PC agent is alive, else cloud. The cloud agent refuses CODE/SHELL/PLAN/MCP. Use "agent" param to target a specific agent (default: claude-code-local). Use tascan_list_agents to discover available agents; track progress with tascan_get_task (its "agent" block).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesThe full task text. START it with CODE: SHELL: PLAN: MCP: RESEARCH: WRITE: or REVIEW: for routing (prefix-only — nothing may precede it), or leave it unprefixed (DEFAULT). The whole text is stored in the task description; the first 140 chars become the title.
agentNoAgent ID or name to dispatch to (default: claude-code-local). Use tascan_list_agents to see options. An unknown agent is an error, never a silent fallback.
priorityNoPriority level (default: normal). The urgent marker is placed AFTER the routing prefix so it never breaks routing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / agent / description
      Previous value: -"Agent ID or name to dispatch to (default: claude-code-local). Use tascan_list_agents to see options."New value: +"Agent ID or name to dispatch to (default: claude-code-local). Use tascan_list_agents to see options. An unknown agent is an error, never a silent fallback."
    • changedInput schema / properties / priority / description
      Previous value: -"Priority level (default: normal)"New value: +"Priority level (default: normal). The urgent marker is placed AFTER the routing prefix so it never breaks routing."
    • changedInput schema / properties / task / description
      Previous value: -"The task description. Prefix with CODE: SHELL: RESEARCH: WRITE: PLAN: for routing, or just plain text."New value: +"The full task text. START it with CODE: SHELL: PLAN: MCP: RESEARCH: WRITE: or REVIEW: for routing (prefix-only — nothing may precede it), or leave it unprefixed (DEFAULT). The whole text is stored in the task description; the first 140 chars become the title."
  2. Changed2 schema fields changed
    • addedInput schema / properties / agent
      Added value: +{
+  "description": "Agent ID or name to dispatch to (default: claude-code-local). Use tascan_list_agents to see options.",
+  "type": "string"
+}
    • changedInput schema / properties / task / description
      Previous value: -"The task description. Prefix with CODE: SHELL: RESEARCH: WRITE: PLAN: for routing, or just plain text. Example: \"CODE: Fix the camera button color in FitCheck/index.html\""New value: +"The task description. Prefix with CODE: SHELL: RESEARCH: WRITE: PLAN: for routing, or just plain text."
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes substantially beyond the annotations: describes automatic pickup/execution, exact routing behavior, cloud agent refusal of CODE/SHELL/PLAN/MCP, default fallback when the local PC agent is dead, and the requirement for agent:dispatch permission. These are non-obvious behaviors an agent must know before invoking.

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?

Dense but well-structured: purpose first, then permissions, routing, fallback, agent targeting, and tracking. Every sentence carries load-bearing operational information; there is no filler or redundancy.

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

Completeness5/5

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

For a 3-parameter tool with no output schema, this description is remarkably complete: it covers invocation, permissions, routing rules, error behavior, default agent, and how to monitor the dispatched task via tascan_get_task. An agent has everything necessary to call it correctly.

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 high-value semantics beyond the schema: the full routing-prefix system, the default agent value, permission nuances per task type, and the pointer to tascan_list_agents for valid agent IDs. This pushes it above baseline.

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?

States a specific verb and resource: dispatches work to an AI agent's inbox for automatic execution. The 'PREFERRED tool for sending work to an AI agent' framing and routing details clearly set it apart from sibling tools like tascan_dispatch_instruction and tascan_send_task_email.

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?

Provides clear operational context: when to target an agent, how routing prefixes select the destination, permission requirements, and how to discover agents or track progress. It does not explicitly state when NOT to use this tool versus alternatives like tascan_dispatch_instruction, so some exclusion guidance is missing.

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