Skip to main content
Glama
CronusL-1141

AI Team OS

by CronusL-1141
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

ecosystem_quick_setup

Set up project ecosystem data sources and scan profiles by recording source rows and saving default or custom profile settings.

Instructions

Record data-source and scan-profile rows for the project.

Creates one DataSource row per entry in sources and persists either the default ScanProfile or the merged custom_profile override. No scan reads these rows: ecosystem_index_update takes its query set, star floor and alert threshold from the project's ecosystem settings (Dashboard ecosystem settings panel), and only GitHub is scanned. So calling this does not change what the next index update discovers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queriesNoKeyword / topic list applied to every created data source's ``config.queries`` field. Optional.
sourcesNoData source kinds to record. Must each be a valid ``DataSourceKind`` value (github / huggingface / npm / pypi / hackernews / producthunt / arxiv / custom); only github is ever scanned. Defaults to ``['github']`` when empty.
use_defaultsNoWhen True (default), persist the built-in default ScanProfile. When False, the API merges ``custom_profile`` over the defaults.
custom_profileNoAdvanced override dict; ignored when ``use_defaults=True``.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.15.0
    • changedInput schema / properties / sources / description
      Previous value: -"Data source kinds to enable, e.g. ``['github', 'huggingface']``.\nMust each be a valid ``DataSourceKind`` value (github / huggingface /\nnpm / pypi / hackernews / producthunt / arxiv / custom). Defaults to\n``['github']`` when empty."New value: +"Data source kinds to record. Must each be a valid\n``DataSourceKind`` value (github / huggingface / npm / pypi /\nhackernews / producthunt / arxiv / custom); only github is ever\nscanned. Defaults to ``['github']`` when empty."
  2. First observedv1.9.0

TDQS

A3.7/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it does disclose the key behavioral trait: the write is effectively inert with respect to scanning, with query set/star floor/threshold sourced elsewhere and only GitHub scanned. It omits secondary traits such as overwrite/idempotency semantics, auth requirements, and error behavior when a source kind is invalid.

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?

Three compact sentences, front-loaded with the core action and followed by the operative caveat. Every sentence earns its place, though the caveat about scans is emphasized more than the primary purpose.

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?

An output schema exists, so return values need no explanation, and the description covers the side-effect profile an agent needs before calling. For a 4-param, no-required-arg setup tool with no annotations, the description is largely complete, missing only auth/prerequisite context.

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 description coverage is 100%, so the schema already documents queries, sources, use_defaults and custom_profile, establishing a baseline of 3. The description restates that sources becomes DataSource rows and that custom_profile is merged over defaults, which adds mild framing but no meaning beyond the schema.

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?

States a specific verb and resource: recording DataSource rows and a ScanProfile for the project. It also names the sibling it must not be confused with (ecosystem_index_update) and clarifies what the tool does not affect, so an agent can tell it apart from the scan/index tools. It stops short of a crisp one-line statement of the tool's purpose, burying it under the caveat.

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 gives strong negative guidance ('No scan reads these rows ... calling this does not change what the next index update discovers') and points at the Dashboard ecosystem settings panel as where real scan configuration lives. However, it never states a positive trigger for when an agent should call this tool instead of others, so usage is only implied.

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

Deploy Server

Other Tools