Skip to main content
Glama
Sign In

Agoranome seller tools

by io.github.Agoranome
OverviewDiscussionsAdmin

Pick odds (not answering yet)

pick_odds
Read-only

Not answering yet. The choice model's calibration slope on held-out picks is 0.70, outside 0.8 to 1.2: its odds would be too sure. Until it answers, a call is refused before any payment. How often would buyer-agent models pick my x402 offer? One signed number: its chance of being picked against the offers models saw in a category's latest Machine Choice Benchmark layouts, at your price, payers, slot and discovery metadata, from a choice model fitted to every benchmark trial (no model call), with its 95% range and what each feature is worth in percent of price. Answers once the model is checked on 100 held-out picks, in a category with 30 priced decisions. Price: $0.005 in USDC per call, paid with x402 inside the tool call. Or send a Skyfire pay or kya-pay token in the kyapay-token header (or in this tool's kyapay-token argument), and this tool charges $0.005 to it. Failed calls aren't charged.

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": {
      "category": "<category>",
      "price": "<price>"
    },
    "name": "pick_odds"
  }
}

Input Schema

NameRequiredDescriptionDefault
slotNoOptional: the position in the list, 1 first; every position averaged if omitted
priceYesYour price per call in USD
payersNoOptional: unique payers in the last 30 days, as the Bazaar shows them (0 if new)
categoryYesThe listing's category
input_schemaNoOptional: whether the listing has an input schema
kyapay-tokenNoA Skyfire pay or kya-pay token made for Agoranome's service, from a client that can't set the kyapay-token header. Leave it out when paying with x402 or the header.
if_none_matchNoSend the answer's ETag back in If-None-Match (over MCP, the if_none_match argument): while the answer is unchanged it comes back as a free 304 Not Modified.
output_exampleNoOptional: whether the listing has an output example

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.2/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior beyond them — the pre-answer refusal with no charge, the $0.005 USDC price via x402, the Skyfire/kya-pay token fallback via header or argument, and 'Failed calls aren't charged.' It also discloses output content (95% range, feature values in percent of price). It does not cover latency or error modes, keeping it below 5.

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

Conciseness2/5

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

The front-loaded 'Not answering yet' is well placed, but the body is a dense run-on: 'One signed number: its chance of being picked against the offers models saw in a category's latest Machine Choice Benchmark layouts, at your price, payers, slot and discovery metadata, from a choice model fitted to every benchmark trial (no model call), with its 95% range and what each feature is worth in percent of price.' Payment mechanics are restated across three sentences and the calibration-slope detail crowds out the essential call semantics.

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 paid, 8-parameter, currently-gated tool with no output schema, the description covers the essentials: why it refuses, what it returns (a signed number, 95% range, feature values), how payment works and that failures are free. Remaining gaps (return format details, timing) are minor given there is no output schema.

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 defines slot, price, payers, category, input_schema and output_example. The description adds only a loose mapping ('at your price, payers, slot and discovery metadata') and notes 'no model call', which is minor added meaning. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The core purpose is stated, but only after a status preamble: 'How often would buyer-agent models pick my x402 offer? One signed number: its chance of being picked...' That is a specific verb and resource, yet the statement is buried in a 50-word run-on and no sibling (e.g. survival_odds) is named to differentiate it. An agent can eventually extract the purpose but not quickly.

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?

It gives real availability guidance: 'Not answering yet... Until it answers, a call is refused before any payment' and 'Answers once the model is checked on 100 held-out picks, in a category with 30 priced decisions.' That is a concrete when-not-to-call condition. However, it names no alternative tool to use while unavailable or for related questions, so routing guidance is only half complete.

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

All Agoranome seller tools toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources