Skip to main content
Glama

BNM Data Shop

by io.github.bnmbnmai
OverviewDiscussionsAdmin

swisspar

GET https://ticks.bnm.farm/swisspar — $0.05 USDC on Base to 0xf59621FC406D266e18f314Ae18eF0a33b8401004. Swissmedic first-authorisation SwissPAR evaluation text GET ?id= is one official text ($0.02). Newest chunk on a plain GET ($0.05); older chunk if they ask (?before, $0.05); newer than a watermark ?since= ($0.05). Unpaid returns HTTP 402. After a valid X-PAYMENT, the same URL returns JSON. Not a new SKU.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoOfficial catalog id. That one official text, $0.02. Same door, not a new SKU.
pageNo1-based page. Page 1 is the newest chunk. Ignored when since/before is set.
sinceNoISO timestamp or official catalog id. Official texts newer than this watermark, $0.05. Empty new set is 304 or recordCount 0.
beforeNoOfficial catalog id or YYYY-MM-DD. Next older chunk on the same URL, another $0.05. Omit for the newest chunk.
x_paymentNoOptional x402 X-PAYMENT value forwarded to the paid GET as the X-PAYMENT header.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / page / description
      Previous value: -"1-based page. Page 1 is the newest chunk. Ignored when before is set."New value: +"1-based page. Page 1 is the newest chunk. Ignored when since/before is set."
    • addedInput schema / properties / since
      Added value: +{
+  "description": "ISO timestamp or official catalog id. Official texts newer than this watermark, $0.05. Empty new set is 304 or recordCount 0.",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / page / description
      Previous value: -"1-based page. Page 1 is the newest chunk. Ignored when since/before is set."New value: +"1-based page. Page 1 is the newest chunk. Ignored when before is set."
    • removedInput schema / properties / since
      Removed value: -{
-  "description": "ISO timestamp or official catalog id. Official texts newer than this watermark, $0.05. Empty new set is 304 or recordCount 0.",
-  "type": "string"
-}
  3. Changed2 schema fields changed
    • changedInput schema / properties / page / description
      Previous value: -"1-based page. Page 1 is the newest chunk. Ignored when before is set."New value: +"1-based page. Page 1 is the newest chunk. Ignored when since/before is set."
    • addedInput schema / properties / since
      Added value: +{
+  "description": "ISO timestamp or official catalog id. Official texts newer than this watermark, $0.05. Empty new set is 304 or recordCount 0.",
+  "type": "string"
+}
  4. First observed

TDQS

B3.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and discloses crucial operational traits: the payment prerequisite ($0.05 USDC on Base to a specific wallet), per-call pricing, HTTP 402 on unpaid requests, the X-PAYMENT header requirement, JSON response after payment, and chunk-ordering semantics. It does not cover rate limits or how X-PAYMENT is obtained, but the high-stakes payment/auth/error behavior is transparent.

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

Conciseness3/5

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

The description is dense with no wasted words, but it is not front-loaded: the opening clause is a wallet address, not the tool's purpose, and the whole thing is a run-on paragraph mixing pricing, semantics, and identity. Compact, but poorly structured for an agent scanning for what the tool does.

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?

For a paid 5-parameter endpoint with no annotations and no output schema, the description covers pricing, payment address, 402 behavior, and the auth header, but leaves the x402 payment flow (how X-PAYMENT is obtained) and the JSON response structure unexplained. 'Not a new SKU' is indecipherable without ecosystem knowledge.

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 100%, and the schema descriptions already embed pricing, chunk semantics, and the page/since/before interaction ('Ignored when since/before is set'), so the description adds little beyond framing these as paid operations on one URL. The description reinforces but does not materially extend the schema's parameter documentation.

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 resource is identifiable — 'Swissmedic first-authorisation SwissPAR evaluation text' — and the GET semantics (?id=, ?before, ?since) imply a retrieval tool, but the description never states the purpose declaratively and leads with payment details (USDC wallet, pricing). The tool's function is tangled with billing mechanics rather than stated as a clear verb-plus-resource.

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 clear usage modes for each paid retrieval scenario: plain GET for the newest chunk, ?id= for one official text, ?before for an older chunk, ?since for newer-than-watermark texts. It does not address tool selection against the 40+ sibling document tools, and the cryptic 'Not a new SKU' note is the only nod to alternatives.

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

All BNM Data Shop toolsInspect
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