Skip to main content
Glama
CHASE MCP Server

CHASE MCP Server

by chase-cps

parse_sva

Read-onlyIdempotent

Extracts SystemVerilog assume and assert property statements into an assume-guarantee contract and returns parsed properties, clocks, skipped items, and signal names for formal checks.

Instructions

Read the assume property and assert property statements of SystemVerilog (a module, a bind file, or the statements alone; text or a file path) as a contract: assumptions and guarantees, with the widths of Verilog, $past, bounded sequences, and disable iff. The directions come from the module ports, or from inputs or outputs (the other signals are of the other kind). Returns the contract, the properties read (label, kind, formula, from_cycle: the cycle from which a property with $past is checked), skipped (statements not read, with the reason), covers, the clock, and undeclared (signals read as 1 bit), and names (hierarchical names: u1__state is u1.state; give them to to_sva). One clock per contract: clock ("posedge clk") chooses it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "parse_sva"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
pathNo
textNo
clockNo
inputsNo
outputsNo
parametersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.2

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnly/idempotent/closed-world; the description adds real behavioral substance: partial parses are reported via `skipped` with a reason, undeclared signals are treated as 1 bit, `from_cycle` explains how $past properties are anchored, and only one clock per contract is allowed. It stops short of describing failure modes or what happens with conflicting clocks.

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 purpose, then dense with genuinely useful facts (return fields, skipped, names, clock rule) that earn their place given there is no output schema. The single run-on paragraph with nested parentheticals and semicolons makes it harder to scan than it needs to be, but there is no filler.

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 no output schema and seven undocumented parameters, the description compensates well by enumerating the return payload (contract, properties with label/kind/formula/from_cycle, skipped, covers, clock, undeclared, names). The remaining gap is that `name` and `parameters` are left unexplained, which matters for a tool whose whole input contract is otherwise undocumented.

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 0%, so the description carries the full burden and does explain several parameters: text vs path, `clock` with the example "posedge clk", and `inputs`/`outputs` with the rule that unlisted signals are the other kind. However, `name` and especially `parameters` (a map of integer parameter overrides) are never explained, leaving two of seven arguments opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: reads assume/assert property statements of SystemVerilog and turns them into a contract of assumptions and guarantees, with the accepted input forms (module, bind file, statements alone; text or path). An agent can tell it is the SVA front-end rather than the spec front-end, but the description never names parse_spec or otherwise explicitly contrasts itself with that sibling.

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?

Usage is implied by the input forms — you call it when you have SystemVerilog assertions to read — and the mention that `names` should be given to to_sva establishes a downstream step. There is no explicit when-not guidance or statement of how this differs from parse_spec, so the agent must infer the choice.

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