Skip to main content
Glama

Silicon Analysts

by io.github.SiliconAnalysts
OverviewDiscussionsAdmin

get_hbm_market_data

Read-onlyIdempotent

Returns 10 HBM market sub-tables: accelerators, specs, marketShare, spotPrices (RETIRED 2026-07-28 — frozen), leadingIndicators, qualificationFeed, revenueForecast, supplierRevenue, validationChecks, bitDemand. Optional table parameter narrows to a single sub-table; omitting returns all 10.

USE THIS for: HBM3/3e/4 generation specs, SK Hynix/Samsung/Micron share of HBM revenue (marketShare: Q2 2026, Counterpoint Research, the latest quarter; the quarterly series and IDC full-year actuals are get_market_dataset dataset='hbm-market-share'; not share of bit shipments), derived HBM bit demand by SKU class and customer type (bitDemand, EB ranges, monthly).

spotPrices is a RETIRED series: no public HBM spot market exists in any generation — HBM sells via annual/multi-year LTAs. Its rows are frozen estimates served for the record with per-row retired marking; for current, sourced HBM pricing use get_market_dataset with dataset='hbm-pricing'.

bitDemand is NOT a workload split — it is a SKU-class/customer-type cut. Dominant HBM SKUs are dual-use, so a training-vs-inference HBM attribution would be dishonest; no public source publishes one.

DO NOT USE for: HBM price history or current HBM pricing (use get_market_dataset dataset='hbm-pricing'); per-accelerator HBM cost in a specific chip (use get_accelerator_costs.costBreakdown.hbmCostUsd); HBM cost in a hypothetical chip cost calc (use calculate_chip_cost with hbmStacks/hbmCost).

Returns INTERNAL_ERROR if the upstream Supabase HBM tables are unreachable. Only two sub-tables refresh on a schedule: qualificationFeed (Mon/Thu) and bitDemand (monthly, 1st). accelerators, specs and validationChecks are hand-curated reference tables, the editorial tables are revised by hand, and spotPrices is frozen (retired 2026-07-28). meta.table_freshness dates each sub-table; meta.data_freshness.stale flags an overdue refresh.

Input Schema

NameRequiredDescriptionDefault
tableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / table / enum
      Previous value: -[
-  "accelerators",
-  "specs",
-  "marketShare",
-  "spotPrices",
-  "leadingIndicators",
-  "qualificationFeed",
-  "revenueForecast",
-  "supplierRevenue",
-  "validationChecks"
-]New value: +[
+  "accelerators",
+  "specs",
+  "marketShare",
+  "spotPrices",
+  "leadingIndicators",
+  "qualificationFeed",
+  "revenueForecast",
+  "supplierRevenue",
+  "validationChecks",
+  "bitDemand"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial operational context: INTERNAL_ERROR on upstream Supabase failure, per-sub-table refresh schedules (qualificationFeed Mon/Thu, bitDemand monthly), which tables are hand-curated vs. frozen, and the meta.table_freshness / meta.data_freshness.stale fields. The spotPrices retirement on 2026-07-28 is disclosed precisely.

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?

Front-loaded with the return shape and the narrowing behavior, followed by well-organized USE / DO NOT USE blocks. It runs long and repeats the ten sub-table names in the opening list and again during explanation, which is a minor redundancy rather than padding.

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?

With no output schema, the description carries the return-value burden itself, exposing the meta freshness/staleness fields and the error mode. For a ten-sub-table aggregator with one optional enum parameter, an agent has everything needed to select a sub-table correctly and interpret freshness.

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?

Schema coverage is 0% though the enum supplies the ten valid values; the description compensates by characterizing several of them (marketShare's source/period and its non-bit-shipment caveat, spotPrices' retired status, bitDemand's SKU-class/customer-type cut) and by explaining the semantics of omitting the parameter entirely (returns all 10). It falls short of describing all ten sub-tables equally.

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?

States a specific verb (Returns) and resource (10 HBM market sub-tables), enumerates them by name, and explains the optional narrowing behavior. It explicitly differentiates itself from siblings like get_market_dataset, get_accelerator_costs, and calculate_chip_cost by naming the separate sub-resources each covers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'USE THIS for' and 'DO NOT USE for' sections, each routing to a named alternative tool or dataset (e.g., 'use get_market_dataset dataset=hbm-pricing'). It also pre-empts a plausible misuse ('bitDemand is NOT a workload split') and corrects a common conflation (share of revenue vs. share of bit shipments).

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

All Silicon Analysts 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