Skip to main content
Glama

Services create listing

services_create_listing

Publish a service listing on Bitroad for GPU compute, inference, data, or research. Choose fixed-price instant purchase or quote-based pricing with optional haggling.

Instructions

Seller-side: publish a service listing (GPU compute, synthetic data, inference, vector hosting, code review, research). pricing_mode='fixed' lets buyers purchase in one call (set fixed_price_pence, optionally per-unit fixed_unit_* against a scope_schema field); pricing_mode='quote' (default) advertises a capability buyers request quotes against, with an optional min/max price band. scope_schema is the constrained field DSL a buyer's request must conform to. Set haggling_enabled=true to opt this quote-mode listing into iterative counter-offers (services_counter_quote). All *_pence values are minor units of the seller's settlement currency. Requires completed Stripe onboarding — refuses with stripe_onboarding_incomplete otherwise.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesShort human-readable title of the service listing.
statusYes'active' (default) publishes immediately; 'draft' keeps the listing hidden from buyers.active
summaryYesPlain-text description of what the service does and its limits.
categoryYesService category. Delegation/envelope spend checks see it as service:<category>.
vat_rate_bpYesVAT rate in basis points (0–10000, e.g. 2000 = 20%) applied to this listing's charges.
pricing_hintNoFree-text pricing guidance shown to buyers (e.g. 'from £50 per 1k rows').
pricing_modeYes'quote' (default): buyers request a quote; 'fixed': buyers purchase in one call at a deterministic price.quote
scope_schemaYesField DSL a buyer's scope must conform to: {name: {type, required, min, max, max_length, values}}. Max 32 fields.
max_price_penceNoInclusive maximum quoted price in pence. Null = no upper bound.
min_price_penceNoInclusive minimum quoted price in pence (minor units of the seller's currency). Null = no lower bound.
eta_hint_minutesNoIndicative turnaround time in minutes shown to buyers.
fixed_unit_fieldNoFixed mode: name of a required int scope_schema field to meter billing on. Set all three fixed_unit_* together.
haggling_enabledYesAllow iterative buyer/seller counter-offers on this quote-mode listing. Ignored for fixed-price listings.
fixed_price_penceNoFixed mode: flat base price in pence. Required when pricing_mode='fixed'.
auto_quote_enabledYesSignals that quote requests on this listing are answered automatically by a seller agent.
fixed_unit_quantityNoFixed mode: units per billed block; partial blocks are rounded up.
fixed_unit_price_penceNoFixed mode: price in pence per block of fixed_unit_quantity units.
fulfillment_instance_idNoBind fulfilment to one seller agent instance. Null/omitted = any seller key with respond_quote may fulfil.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

The description adds behavioral details beyond the annotations, such as the Stripe onboarding requirement and refusal with 'stripe_onboarding_incomplete,' and notes that haggling_enabled is ignored for fixed-price listings. This goes beyond the basic readOnly/destructive flags in the annotations.

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?

The description is packed with useful information and structured around key concepts (pricing modes, scope schema, Stripe requirement). While it is dense, it remains focused and avoids unnecessary filler, earning a high score for conciseness given the tool's complexity.

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?

Given the tool's complexity (18 parameters, nested objects, no output schema), the description adequately covers essential context: the purpose, pricing modes, scope DSL, and a key error condition. It does not mention every edge case, but it provides enough for an agent to decide when and how to use the tool.

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?

Although the schema descriptions cover 100% of parameters, the description adds relational context, such as how fixed_unit_* fields must be set together and how scope_schema constrains buyer requests. This enriches the schema's individual parameter descriptions without redundancy.

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?

The description clearly states the tool's purpose: 'Seller-side: publish a service listing.' It specifies the resource (service listing) and the action (publish), and distinguishes it from buyer-side tools by listing service categories like GPU compute and synthetic data.

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 provides some usage conditions (e.g., requires completed Stripe onboarding) and explains the fixed vs. quote pricing modes, but it does not explicitly differentiate this tool from the sibling 'seller_create_listing' or state when to prefer one over the other. Alternatives are not named.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bitroadai/bitroad-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server