Skip to main content
Glama
science-ai-mcp-server

science-ai-mcp-server

by SelfPy

Start Article Writer Pipeline

start_writer_pipeline

Enqueue a writer-pipeline job for an existing WriterSession and get a jobId immediately, then poll status until done, failed, or aborted.

Instructions

Not available with an API key during the Article Writer's private beta: the server answers every API-key call to this tool with 404. Once the writer is public: enqueue a writer-pipeline job for an existing WriterSession. Returns immediately with a jobId; the orchestrator-worker claims it within ~5 seconds. Default section is step_7_5 — the auto-chain that replaces the three buttons in Step 7.5. Use get_writer_pipeline_status to poll until status is 'done', 'failed', or 'aborted'. Writer steps are billed in Science AI Journal credits.

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": {
      "sessionId": "<sessionId>"
    },
    "name": "start_writer_pipeline"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoIf true, abort any existing queued/running job for this (sessionId, section) and enqueue fresh.
sectionNoWhich section to run. Default 'step_7_5' (the code-search → adapt → verify → simulate chain).
languageNoSimulation language override (python | r | matlab | ...).
sessionIdYesWriterSession id you already own. Create one via the web UI at /writer first; the MCP server does not own the session-creation flow today.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.3

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the async enqueue-and-return contract, a ~5 second worker claim latency, credit billing, and the beta 404 behavior. It does not cover error handling for an invalid sessionId or permission/ownership failures, which is the remaining gap.

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?

Information-dense and front-loaded with the availability caveat that would otherwise waste a call. Slightly sprawling as a single block covering availability, mechanics, defaults, polling, and billing, but every sentence contributes.

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?

No output schema exists, and the description properly explains the return value (jobId) and the follow-up polling path. Ownership prerequisite is stated; only failure modes for bad sessionIds are left implicit.

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?

Schema coverage is 100%, so all four parameters are already documented, including the section enum and force semantics. The description only adds the 'step_7_5 replaces the three buttons in Step 7.5' framing, which is marginal over the schema's own 'code-search → adapt → verify → simulate chain' explanation.

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 — 'enqueue a writer-pipeline job for an existing WriterSession' — and immediately frames the asynchronous model with 'Returns immediately with a jobId'. An agent can distinguish this from get_writer_pipeline_status purely from the text.

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 says to use get_writer_pipeline_status to poll until 'done', 'failed', or 'aborted', and states the prerequisite that a WriterSession must already exist (create it via the web UI). It also gives a hard when-not-to-use rule: API-key calls return 404 during the private beta.

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