Skip to main content
Glama

BNM Data Shop

by io.github.bnmbnmai

firm-check

Free cross-door search of official caches: Form 483, FDA warning letters, FDA untitled letters, FTC BCP warning letters, Ofwat enforcement, Ofgem enforcement, CFPB orders, OCC C&Ds, FDIC orders, and the FDA import-alert catalog. Not a paid SKU. Hits name the door, the id or page to buy, and fetchedAt/asOf. One official text is GET ?id= ($0.02). The page of newest 10 official texts is $0.05. The import-alert table stays the entire current table at $0.05. Does not return letter bodies or the full import-alert table.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFirm, institution, bank, company, FEI, CMS, or import-alert number. Free. Not charged.

TDQS

A4.4/5.0
Behavior5/5

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

The description discloses result shape (hits name the door, id/page to buy, fetchedAt/asOf), costs for follow-up documents, and negative behavior (does not return letter bodies/full import-alert table). Since annotations are not structured read/destructive hints, the description carries the burden and fully covers it.

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 dense but front-loaded with the core purpose, followed by pricing and exclusions. Every sentence carries information; a bulleted or more separated structure would be marginally clearer, but there is little waste.

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

Completeness5/5

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

For a one-parameter search tool with no output schema, the description covers what the tool searches, what a hit contains, what follow-ups cost, and what it deliberately omits. An agent has enough context to invoke q correctly and set expectations about the response.

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 q parameter is described as 'Firm, institution, bank, company, FEI, CMS, or import-alert number. Free. Not charged.' The main description does not need to add much, and it doesn't, so the baseline 3 applies.

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 opens with 'Free cross-door search of official caches' and enumerates the exact caches covered, making the verb and resource unmistakable. It is clearly distinct from single-door siblings like warning-letters and import-alerts.

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?

It states this is a free cross-door search and explicitly notes what it does not return ('Does not return letter bodies or the full import-alert table'). It does not name alternative tools like search or get-one, but it gives enough pricing and limitation context for an agent to choose it for a broad search and route follow-up purchases to ?id= or page calls.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation3/5

Most tools map cleanly to distinct regulatory document collections (FDA, EPA, FDIC, etc.), so the majority are unambiguous. However, 'search' and 'firm-check' both offer free search with overlapping scope, and 'get-one' vs 'get-page' are easily confused payment operations. Similar prefixed names like mariners, mariners-d7/d8/d11 and gmp/gmp-md add further boundary fuzziness.

Naming Consistency3/5

The bulk of tools follow a consistent lowercase-hyphenated source-slug convention (aaib-reports, cder-reviews, cfpb-orders), which is predictable. But utility tools break the pattern with imperative/descriptive names (search, firm-check, get-one, get-page), and 'ticks' is a bare noun that doesn't fit either style. The mixed conventions are readable but not uniform.

Tool Count2/5

At 46 tools, this is a heavy surface that will be unwieldy for an agent to navigate and select from. Each tool does represent a distinct data product, but the sheer volume exceeds what earns its place in a coherent MCP tool set. A door-based catalog design might work better with a smaller number of parameterized tools.

Completeness4/5

The core workflow is well covered: per-door search, cross-door search, single-document retrieval via ?id=, paginated page retrieval, and payment handling are all present. Minor gaps exist, such as no tool to enumerate all available doors/catalogs or inspect schemas, and firm-check returns only citations rather than bodies. Overall it's a complete access lifecycle for the data-shop domain.

Resources