Skip to main content
Glama

Start a research project

start_project

Delegate research, data analysis, or writing tasks to cloud agents with local files; approve the plan before credits are charged or set a credit cap for unattended runs.

Instructions

Hand a research, data analysis or writing task to HumanPen's cloud agents, with local files as its input: they scope it with the user, propose a plan, do the work, have it reviewed and deliver files. COSTS CREDITS once a plan is confirmed (charged by use; there is no price up front): show the user the plan and get their agreement before act_on_project confirm_plan, unless they set autonomy with a max_credits. Needs an API key with "Research projects" ticked.

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": {
      "request": "<request>"
    },
    "name": "start_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoThe language to write in, e.g. en or zh
filesNoAbsolute paths of input files (data, drafts, papers)
titleNoA name for the project; one is made from the request if omitted
requestYesWhat the user wants done, in their words: the goal, the deliverables, any constraints
autonomyNoLet it run unattended within a credit cap the user set; omit to stop for the user at every step

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say this is a non-read-only, non-destructive operation; the description adds the crucial economics — credits are charged only once a plan is confirmed, priced by use with no up-front figure — plus the permission requirement and the consent/autonomy policy. These are exactly the facts an agent needs before triggering a costly, human-in-the-loop workflow.

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 cost, then consent, then auth — a sensible priority order with no filler. The second sentence is dense and carries several parenthetical clauses, which costs it a point on readability.

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 five-parameter tool with a nested autonomy object and no output schema, the description covers workflow, cost model, consent gate, and auth scope — everything needed to invoke it responsibly. The only minor omission is what the call returns (presumably a project handle), which the sibling get_project can resolve.

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 still adds value by framing autonomy as a user-agreed credit cap that lets the project run unattended, and by tying confirm_plan approval to the credit decision. It does not explain the files/request interaction beyond the schema, so it stops short of a 5.

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 — handing a research, data analysis or writing task to cloud agents with local files as input — and outlines the agent workflow (scope, plan, work, review, deliver). This clearly separates it from siblings like act_on_project, message_project and get_project, which are lifecycle operations on an already-started project.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly conditions the call: show the user the plan and get agreement before act_on_project confirm_plan, unless autonomy with max_credits was set. It names the follow-up sibling tool and states the prerequisite API key scope ("Research projects" ticked), leaving little to inference.

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