Skip to main content
Glama

SourceGeek

Plan tasks in a project

plan_tasks

Add tasks to a SourceGeek project's board, in To Do, in the order given, to an existing project or to a new one this call creates. Nothing runs and nothing is charged: a task starts only when it is started. Each task is one piece of work a SourceGeek chat finishes on its own (a market map, sourcing for one market, a shortlist, outreach drafts) and sees only its own description and the project's brief, so write each description self-contained: the goal, the context it needs and the expected output. A task can wait on earlier ones: started together, it starts by itself once they are ready for review, with their results. Returns the project and each task's key and URL.

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": "plan_tasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
tasksYes
projectNoAn existing project's id (prj_…) or key (e.g. SBE). Leave out to create newProject.
newProjectNoCreate a project, shared with the workspace, and plan into it. Only when the user wants a new project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Well beyond the annotations: it discloses that nothing executes or is charged, that each task sees only its own description and the project brief (an isolation constraint on how descriptions must be written), that dependent tasks auto-start once prerequisites are ready for review with their results, and what is returned. Only the absence of failure/permission behavior keeps this from the top.

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-loads the action, then cost/execution semantics, then how to write a task, then dependencies, then return value — a logical progression with no filler sentences. It is dense as one uninterrupted paragraph, which makes the dependency and description-authoring rules slightly harder to scan than they could be.

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?

Covers the nested-object complexity (tasks array plus optional new project), the execution model, dependency behavior, description authoring, and the return shape (project plus each task's key and URL) despite no output schema. An agent has everything needed to call this correctly, including the max-10 batching limit implied by the schema.

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?

The description adds authoring guidance for the description field ("write each description self-contained: the goal, the context it needs and the expected output") and asserts task ordering, which the schema does not state. However, the `after` dependency parameter and `template` enum semantics are left entirely to the schema, so the added meaning is partial against 67% coverage.

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 ("Add tasks to a SourceGeek project's board"), plus the placement ("in To Do"), ordering ("in the order given"), and both target modes (existing project or a new one this call creates). It also implicitly separates itself from start_tasks by noting a task "starts only when it is started."

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 clear conditional guidance: use newProject "Only when the user wants a new project," otherwise attach to an existing project, and makes explicit that this call does not execute anything — a real decision point against start_tasks. It stops short of naming sibling tools as alternatives, so it is clear context rather than full when/when-not routing.

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