Skip to main content
Glama

Scrutica

by io.github.davidgringras

scrutica_get_supply_chain

Read-only

Return supply-chain relationships for one or more organizations. direction = 'upstream' traces suppliers (who feeds this entity); 'downstream' traces customers (who depends on this entity); 'both' returns both. Each edge: source_org_id, target_org_id, relationship_type, supply_share (where disclosed), price_correlation_3m (3-month rolling, where available), data_source. Dataset: 18,999 edges from a licensed supply-chain database (held under subscription, not redistributed) plus SEC Exhibit 21 (substrate snapshot 2026-09-01).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
org_idNoAlias for org_ids; a single id may be passed as a bare string.
org_idsNoREQUIRED. Scrutica org IDs in 'org-<slug>' format (e.g. ['org-nvidia', 'org-tsmc']), 1-5 of them. Optional in the schema only so the single-id aliases below can stand in.
directionNoboth
company_idNoAlias for org_ids.

TDQS

A4.2/5.0
Behavior4/5

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

With readOnlyHint=true, safety is already declared; the description adds dataset provenance (licensed subscription plus SEC Exhibit 21 snapshot), the fields returned, and data-availability caveats. It also explains 'upstream'/'downstream' semantics, which annotations do not. It does not cover auth or rate limits, but those are not critical for a read-only query.

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

Conciseness5/5

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

Four sentences, each carrying distinct info: operation, direction semantics, edge schema, and data provenance. No filler or restatement of what the schema already says.

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?

No output schema exists, so the edge-field enumeration is valuable. The data-source licensing note and snapshot date set expectations. Missing explicit guidance on when to use alternatives is the main gap, but for a read-only graph query this is close to complete.

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?

The schema documents org_id/org_ids/company_id aliases and limit bounds; the description adds the decisive semantic content: what 'upstream', 'downstream', and 'both' mean. This is exactly the parameter-level guidance an agent needs to pick the correct direction. Limit and org-ID format are left to schema, and with 60% coverage the description only partially compensates.

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?

Opens with 'Return supply-chain relationships for one or more organizations' — a specific verb, resource, and scope. The direction definitions and edge-field list clearly distinguish it from sibling entity tools like scrutica_get_company and scrutica_search. There is no ambiguity about what resource is being queried.

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 makes the tool's scope clear but never states when to prefer it over sibling tools or when not to use it. There is no explicit alternative or exclusion, so an agent must infer applicability from the tool name. Direction semantics are parameter guidance, not tool-selection guidance.

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

All Scrutica 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

A4.4/5.0
Disambiguation5/5

Each tool targets a clearly distinct resource or action: canonical entity/facility/program lookups, free-text search, supply-chain traversal, BIS query versus BIS change-log, FLOP estimation, and methodology docs. Cross-references explicitly redirect likely-confused intents, such as using scrutica_query_export_controls for entity designations and scrutica_entity_list_changes for changes, so misselection is unlikely.

Naming Consistency4/5

The naming is mostly consistent: scrutica_get_* for canonical lookups, plus clear action-style names like scrutica_search, scrutica_query_export_controls, and scrutica_estimate_flops. The main deviation is scrutica_entity_list_changes, which reads as a noun phrase rather than a verb-first tool name, so the pattern is coherent but not perfectly uniform.

Tool Count5/5

Ten tools is well calibrated for this server's broad but focused domain coverage. Each meaningful data area gets one or two dedicated tools—companies, facilities, sovereign programs, supply chain, export controls, scenarios, methodology, and FLOP estimation—with no count-inflating duplicates.

Completeness4/5

The read-side surface is largely complete: search, get-by-ID, change-tracking, relationship traversal, scenario retrieval, and methodology lookup all exist. The main gap is that some methodology topics describe metrics or indices—such as cost-index and compute-visibility index—without an obvious dedicated tool for retrieving those metric values directly.

Resources