Silicon Analysts

calculate_chip_cost

Read-onlyIdempotent

Pure-function chip cost estimator. Given die dimensions (mm), process node, and optional packaging/HBM parameters, returns: estimatedChipCost (USD), dieArea (mm²), grossDiesPerWafer, frontendYield (%), totalYield (%), and a costBreakdown {waferCostPerGoodDie, packagingAndTestCost, hbmCost, marginCost}.

USE THIS for: hypothetical chip cost modeling, sensitivity analysis, fabless tapeout decisions.

DO NOT USE for: published cost of an existing accelerator (use get_accelerator_costs); wafer pricing only (use get_wafer_pricing).

Required: dieWidth, dieHeight (1–33 mm reticle limit). Errors with INVALID_PARAMS if outside bounds. processNode defaults to tsmc-n5; valid nodes via get_wafer_pricing. Estimates are directional ±15–20%.

Optional energy adder: pass energyRegion (texas|ohio|arizona|china|korea|taiwan|germany) to get a conditional energy block — regional manufacturing-electricity cost per die (SA estimate; wafer price already embeds foundry energy, so treat it as a scenario delta). energyFacilityOverhead=false drops the ~1.75× facility multiplier.

Optional substrate scenario: pass substrate=panel-310x310 to model CoPoS panel-level assembly — applies the midpoint of Yole's realistic 20–30% panel cost-savings band to the packaging cost ONLY (silicon GDPW unchanged; panels are back-end). Conditional substrateScenario block + SA-scenario meta note. TSMC CoPoS: pilot ~June 2026, mass production 2028–29 — a forward-looking scenario, not a quote.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`volume`	No
`hbmCost`	No
`dieWidth`	Yes
`testCost`	No
`dieHeight`	Yes
`hbmStacks`	No
`substrate`	No
`waferCost`	No
`yieldModel`	No
`processNode`	No
`backendYield`	No
`energyRegion`	No
`marginTarget`	No
`defectDensity`	No
`packagingCost`	No
`packagingType`	No
`kgdTestCoverage`	No
`energyFacilityOverhead`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 6, 2026
- addedInput schema / properties / kgdTestCoverage
```
Added value: +{
+  "maximum": 100,
+  "minimum": 0,
+  "type": "number"
+}
```

Changed1 schema field changedJul 5, 2026

addedInput schema / properties / substrate

Added value: +{
+  "enum": [
+    "wafer-300mm",
+    "panel-310x310"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedJul 5, 2026

addedInput schema / properties / energyFacilityOverhead
```
Added value: +{
+  "type": "boolean"
+}
```

addedInput schema / properties / energyRegion

Added value: +{
+  "enum": [
+    "texas",
+    "ohio",
+    "arizona",
+    "china",
+    "korea",
+    "taiwan",
+    "germany"
+  ],
+  "type": "string"
+}

First observedMay 31, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations declare read-only/idempotent, but the description goes far beyond by disclosing error behavior (INVALID_PARAMS), uncertainty (±15–20%), default process node, and scenario-specific caveats (energy as delta, CoPoS as forward-looking). No contradictions with annotations, which are reinforced by the 'Pure-function' framing.

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?

Well-structured with clear sections and front-loaded purpose. Every sentence provides operational guidance (defaults, error behavior, scenario caveats). Length is justified by the tool's complexity and the density of useful information.

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?

No output schema, but description enumerates all returned fields with units, explains conditional blocks (energy, substrateScenario), provides bounds, defaults, accuracy, and references siblings for external data. For a complex estimator with 18 parameters, this is comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage for 18 parameters, but the description explains required bounds (1–33 mm), default processNode, energyRegion semantics (scenario delta), energyFacilityOverhead effect (~1.75× multiplier), and substrate scenario behavior—substantially compensating. Remaining numeric params (hbmCost, testCost, etc.) are inferable from names.

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 a specific verb ('estimates') and resource ('chip cost'), enumerates the computed outputs, and explicitly contrasts with sibling tools (get_accelerator_costs, get_wafer_pricing). This leaves no ambiguity about the tool's scope.

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' guidance, naming sibling tools for alternatives (get_accelerator_costs, get_wafer_pricing) and even directing users to get_wafer_pricing for valid process nodes. This is model usage guidance.

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

All Silicon Analysts tools Inspect

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

Need Help?