circuit-agent

Overview Schema Source Related Servers Discussions Admin

size_hold_up_capacitor

Read-onlyIdempotent

Size an MLCC reservoir bank for a brown-out ride-through window in EFFECTIVE farads, then report the marked value you must actually buy.

Instructions

Size an MLCC reservoir bank for a brown-out ride-through window in EFFECTIVE farads, then report the marked value you must actually buy. Solves C = I·t/ΔV for the required effective capacitance and divides by the retention at the worst-case bias in the window, because sizing from the marked value is how a design that 'passes' delivers 0.85 ms of hold-up when the spec asked for 20 ms. Reports the achieved hold time, the shortfall, and the required marked capacitance.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "load_current_ma": "<load_current_ma>",
      "v_start": "<v_start>",
      "v_floor": "<v_floor>",
      "required_hold_time_ms": "<required_hold_time_ms>"
    },
    "name": "size_hold_up_capacitor"
  }
}

Input Schema

Name	Required	Description	Default
`rated_v`	No	Capacitor rated voltage. Defaults to 2x v_start to keep bias derating near 50%.
`v_floor`	Yes	Minimum voltage the load tolerates (brown-out floor), in volts.
`v_start`	Yes	Rail voltage at the moment the source collapses, AFTER any ORing diode drop — not the nominal input.
`ambient_c`	No	Operating ambient in °C.
`case_size`	No	EIA case code (0402/0603/0805/1206/1210).	0805
`dielectric`	No	EIA dielectric: X5R, X7R, X8R, C0G/NP0.	X5R
`tolerance_pct`	No	Capacitance tolerance in percent.
`load_current_ma`	Yes	Load current drawn from the reservoir during the outage, in mA.
`hours_in_service`	No	Expected service life in hours.
`required_hold_time_ms`	Yes	Required ride-through duration in milliseconds.

Output Schema

Name	Required	Description
`notes`	Yes	Human-readable findings: which term dominates, what to change, and any caveat.
`passes`	Yes	True when achieved meets or exceeds required.
`v_floor`	Yes	Brown-out floor the rail must stay above.
`v_start`	Yes	Rail voltage at the start of the outage, after any diode drop.
`margin_ms`	Yes	Achieved minus required; negative means the design fails.
`shortfall_uf`	Yes	Effective capacitance still missing; zero when the design passes.
`load_current_ma`	Yes	Load current used.
`achieved_hold_time_ms`	Yes	What the sized bank actually delivers.
`marked_capacitance_uf`	Yes	The reel value you must buy to get that effective value.
`required_hold_time_ms`	Yes	The spec: how long the rail must survive.
`required_capacitance_uf`	Yes	Effective capacitance the physics demands (I·t/ΔV).
`effective_capacitance_uf`	Yes	Effective capacitance the sized part delivers.
`required_marked_capacitance_uf`	Yes	Alias of marked_capacitance_uf, kept for clarity.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.16.0Oct 22, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is free. The description adds real behavioral substance: the computation path (solve C = I·t/ΔV, then divide by retention at worst-case bias) and the reported outputs (achieved hold time, shortfall, required marked capacitance). It does not disclose the derating model's limits or assumptions, keeping it from a 5.

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?

Purpose and outputs are front-loaded in the first sentence, and the second sentence carries the technical method. The 'because sizing from the marked value...' clause is slightly discursive but earns its place by flagging the classic failure mode. Trimming that clause to one clause would make it a 5.

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?

With an output schema present, return values need not be documented, yet the description still names them. Annotations cover safety, and the description covers the computational model for a 10-parameter tool. What's missing is any statement of the derating assumption limits (temperature/aging interplay) for the tolerance and hours_in_service inputs.

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 100%, so baseline is 3, but the description earns extra credit by mapping the formula variables (I, t, ΔV) onto the parameter set, which tells the agent how load_current_ma, required_hold_time_ms, v_start and v_floor combine. It also frames the effective-vs-marked distinction that governs rated_v.

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 and resource — 'Size an MLCC reservoir bank for a brown-out ride-through window' — and explicitly names the two outputs (effective farads and the marked value to purchase). This is clearly distinguishable from the sibling calculate_effective_capacitance, which measures rather than sizes.

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 intended scenario (brown-out ride-through sizing) is implied clearly, but the description never states when to prefer this over calculate_effective_capacitance or analyze_power_tree, nor any prerequisites. The 0.85 ms vs 20 ms anecdote explains why the tool exists rather than when to call it.

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

Deploy Server