Galactic Bridge: sourcing and delivery to Africa

Submit a sourcing request for a person

submit_sourcing_request

Create a real request for a person who wants to buy and receive goods. Use ONLY with the person's permission and their real contact details: our team will contact them. Returns a reference and a PRIVATE tracking key: give both to the person and keep them private.

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": {
      "product": "<product>",
      "name": "<name>",
      "country": "<country>",
      "person_consent": "<person_consent>"
    },
    "name": "submit_sourcing_request"
  }
}

Input Schema

Name	Required	Description
`city`	No
`lane`	No	Optional preferred route for Uganda
`name`	Yes	The person's name
`email`	No
`links`	No	Optional product links (https)
`phone`	No	With country code, e.g. +256…
`budget`	No	e.g. 'US$2,000' or 'UGX 7,000,000'
`country`	Yes	Delivery country (Uganda is live; others go to route review)
`product`	Yes	What they need: product, specifications, quality, any brand or model
`quantity`	No
`agent_name`	No	Your assistant's name, e.g. 'claude' or 'chatgpt' (shown to our team)
`person_consent`	Yes	true = the person agreed to be contacted by Galactic Bridge about this request

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare write, open-world, and non-idempotent behavior; the description adds value beyond that by stating a human team will contact the person, that a reference is returned, and that a PRIVATE tracking key must be handed over and kept secret. It does not cover failure modes, duplicate handling, or whether a request can be cancelled, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: purpose first, then the consent/contact constraint, then the return and privacy handling. Every clause carries information an agent needs, and nothing is redundant.

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?

For a 12-parameter submission tool with no output schema, the description covers the essential contract: consent is required, a human follows up, and two sensitive values come back. It is slightly thin on contact-method requirements and what a rejected or duplicate submission looks like.

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 75%, so the schema already documents most parameters and the 3 baseline applies. The description hints that 'real contact details' are mandatory, but the schema marks email and phone as optional and never states that at least one is required — a gap the description could have closed and did not.

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?

The description gives a specific verb and resource: 'Create a real request for a person who wants to buy and receive goods.' That is distinct from siblings like track_request or estimate_delivered_cost, though it never names an alternative. The emphasis on 'real' signals this submits an actual order rather than a quote or estimate.

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?

'Use ONLY with the person's permission and their real contact details' sets a clear precondition for calling the tool. It does not point to alternatives (e.g., estimate first, or use track_request afterwards), so the routing guidance stops short of naming when not to use it.

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

All Galactic Bridge: sourcing and delivery to Africa tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?