Skip to main content
Glama

Agoranome buyer checks and market data

Fair pick

fair_pick
Read-only

Which paid API should my agent call for this job? Paid x402 and MPP endpoints that fit a job in plain words, under your price per call, ranked by a published rule no seller can pay for: only offers that answered payable this week, those that asked what they list first, then a Fair Offer block, then the closer fit, then the lower price, two places a seller at most. From the inspector's signed weekly tables; anyone can recompute it. Free at agoranome.com/pick. Free: no payment is asked.

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": {
      "job": "<job>"
    },
    "name": "fair_pick"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesWhat the endpoint should do, in plain words
ruleNoOptional: pick-2 (the default, the inspector's public rule) or pick-1, its first
limitNoHow many to return
marketNoOptional: one market only
budget_usdNoOptional: the most to pay for one request, in USD
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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / rule / description
      Previous value: -"Optional: pick-2 (the default) or the inspector's pick-1"New value: +"Optional: pick-2 (the default, the inspector's public rule) or pick-1, its first"
  2. Changed1 schema field changed
    • addedInput schema / properties / rule
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "pick-1",
      +        "pick-2"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional: pick-2 (the default) or the inspector's pick-1",
      +  "title": "Rule"
      +}
  3. Added

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the description's job is to add context, and it does: the ranking is from 'the inspector's signed weekly tables', is recomputable by anyone, cannot be bought by a seller, and is limited to offers 'that answered payable this week', with at most two slots per seller. It also states the call is free and asks for no payment, which is materially useful for a paid-endpoint directory. It omits result shape and whether results are paginated or cached beyond weekly, so a 4 rather than 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.

Conciseness2/5

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

Purpose is front-loaded in the first clause, but the middle sentence is a long run-on that strings together five ranking criteria in one breath, and the tail is redundant: 'Free at agoranome.com/pick. Free: no payment is asked.' repeats the same fact twice in a single line. It is dense to the point that the actionable content is hard to extract.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Six parameters, no output schema, and no annotation gaps, so the description needs to say what comes back. It implies a ranked list of offers with at most two per seller, but never states the result shape, whether each entry carries price/endpoint/offer id, or how limit interacts with the ranking — a real gap for a discovery tool whose output the agent must then act on.

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 baseline is 3. The description reinforces that the job is in plain words, that the constraint is price per call, and that there are x402 and MPP markets, plus 'two places a seller at most' which faintly explains result composition, but it adds no syntax, format, or default guidance 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?

The opening question plus the phrase 'Paid x402 and MPP endpoints that fit a job in plain words' names the verb (find/rank) and the resource (paid endpoints) concretely, and the ranking-rule sentence makes clear this returns an ordered shortlist rather than a raw search. It never names a sibling, so an agent must infer for itself why it would call fair_pick rather than check_fair_offer or check_offer for a specific offer.

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?

'under your price per call' implies the budget-bounded discovery case, and 'only offers that answered payable this week' hints at the freshness filter that selects this tool. But there is no explicit when-to-use/when-not statement and no mention of the verification siblings, so an agent is left to infer that fair_pick is for discovery while check_offer/check_fair_offer are for validating a known offer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.