Skip to main content
Glama

SourceGeek

Start SourceGeek on tasks

start_tasks
Destructive

Start SourceGeek on tasks of one project: each runs in a SourceGeek chat of its own, as the user, and costs one chat run of the workspace's credits. A running task can search the web and third-party data sources and use the user's connected apps. A task that waits on others not yet ready for review is queued instead and starts by itself, with their results, once they are; on a task that already ran, the instruction goes to its chat as a follow-up. Tasks report back in SourceGeek (the project's chat, the inbox and email) when they are ready for review or fail. Returns what started, what waits and what couldn't start.

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": {
      "tasks": "<tasks>"
    },
    "name": "start_tasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
tasksYesEvery task to start, all of one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=true, so the bar is lower. The description adds genuinely useful behavior beyond that: each start consumes one chat run of workspace credits, tasks execute as the user with web and connected-app access, unchanged-blocked tasks queue and self-start, and re-started tasks become follow-ups. However it never explains what the destructiveHint actually destroys (the credit spend is the closest hint) or whether a running task can be aborted, leaving the risk profile partly inferred.

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 and cost, then edge-case behavior, then reporting and return shape — a sensible order. Some sentences are long and clause-chained (the queuing sentence especially), costing a little readability, but nothing is filler.

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?

There is no output schema, yet the description states what is returned (what started, what waits, what couldn't start) and covers reporting channels, cost, queuing, and follow-up semantics. For a single-parameter launching tool this leaves no material gap an agent needs before calling it.

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, and the description goes further by clarifying that the optional instruction serves either as extra scope beyond the task description or as the follow-up for an already-run task, and that all entries must belong to one project. It does not restate the 1-10 item limits, which is fine since the schema carries them.

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?

Specific verb and resource: "Start SourceGeek on tasks of one project", with the unit of work (one chat per task, all in one project) made explicit. It is clearly distinguishable from list_tasks/plan_tasks by the fact that it launches execution rather than reading or drafting, though it never names a sibling to route against.

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 implies when this applies (tasks ready to be run) and covers important edge cases — queued tasks that wait on others, and tasks that already ran receiving a follow-up. But there is no explicit when-not-to-use guidance and no reference to planning or listing alternatives, so selection still requires inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources