Skip to main content
Glama
gokeshenzhen

io.github.gokeshenzhen/traceweave

by gokeshenzhen

verify_window

Check temporal properties over clock windows in waveforms, returning a precise holds/counterexample verdict with sampled values to prove or disprove RTL behavior.

Instructions

Evaluate a temporal predicate over a clock window and return a precise verdict (holds) plus a concrete witness/counterexample (cycle + sampled values). You state the predicate; the tool checks it against the waveform over thousands of cycles you cannot read yourself. Templates, not a DSL: a term is {signal, op, value} (op: eq/ne/gt/ge/lt/le/is_x/is_known); a predicate is a list of terms (implicit AND — run two calls for OR). Modes: always(P), never(P), eventually(P), implication (A |-> B within N cycles, the protocol-response template; set overlap=false for |=> = a stability/hold property where B must STILL hold the NEXT cycle, e.g. HTRANS/valid held through a wait state), and sequence (the per-accepted-beat increment of a signal — address-stride checks like AHB haddr +stride; supports modulo for WRAP bursts and restart_when for burst boundaries). x/z cycles are reported as unknown (never silently passed); an implication whose response window runs past end-of-trace is reported inconclusive (never silently failed). On a finding it sets violating_signal + a next_action to explain_signal_driver (bus facts do not self-attribute master/slave). Use to prove/disprove an RTL inference in one call. Reads existing waveforms only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
edgeNoClock edge to sample on. Default posedge.posedge
modeYesTemporal template to evaluate.
clockYes1-bit clock signal full path.
deltaNosequence only: check the per-accepted-beat increment of one signal. predicate is the accepted-beat gate (e.g. hready==1 && htrans active). E.g. AHB byte INCR: {signal:'top.haddr', value:1}. For WRAP bursts pass modulo = burst region bytes (size*len) so the wrap-around beat is accepted via (cur-prev) mod modulo. Pass restart_when (a predicate, e.g. htrans==NONSEQ) to re-seed at each new burst so burst boundaries are not flagged.
overlapNoimplication only. true (default, |->): the response window includes A's own cycle. false (|=>): the window starts the NEXT cycle [i+1, i+within] — use this for a stability/hold property ('B must STILL hold next cycle', e.g. HTRANS/valid held through a wait state) where A already implies B on its own cycle. With overlap=true such a property is a VACUOUS pass (flagged in result.vacuous + warnings); overlap=false requires within_cycles>=1.
predicateNoalways/never/eventually: list of {signal, op, value} terms, AND-combined.
wave_pathYesWaveform (FSDB or VCD).
antecedentNoimplication only: the A predicate (list of terms).
consequentNoimplication only: the B predicate that must follow A.
cursor_nameNoOptional explicit cursor name for the witness/counterexample.
cursor_noteNoOptional note for the registered cursor.
end_time_psNoWindow end. -1 = end of trace.
start_time_psNoWindow start (ps int, '@cursor', or unit literal). Default 0.
within_cyclesNoimplication only: B must hold within this many cycles of A. The response window is [i, i+within] when overlap=true (includes A's cycle) or [i+1, i+within] when overlap=false. Default 1.
Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses edge-case handling: x/z cycles are reported as unknown and never silently passed; an implication running past end-of-trace is inconclusive and never silently failed. It also reveals side effects/outcomes: on a finding it sets violating_signal plus next_action to explain_signal_driver, and notes that two calls are needed for OR semantics.

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?

The description is long but dense and every clause earns its place. It front-loads the core purpose, then efficiently covers templates, modes, edge cases, output behavior, and intended use. Semicolon-separated lists and mode names keep complex information scannable.

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?

There is no output schema, so the description appropriately explains return behavior: verdict, witness/counterexample with cycle and sampled values, vacuous pass/warnings, inconclusive results, and the violating_signal/next_action mechanism. For a tool with 14 parameters, nested objects, and multiple mode-dependent parameter sets, the description is complete enough for an agent to select and invoke it correctly.

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 description coverage is 100%, so the baseline is 3. The description adds meaningful semantic guidance beyond the schema: term format, implicit AND, mode-specific intent, overlap behavior for |=> stability properties, and concrete examples like AHB haddr + stride and restart_when for burst boundaries. It does not exhaustively walk through all 14 parameters, but it covers the semantically tricky ones such as delta, overlap, and restart_when.

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 and resource: "Evaluate a temporal predicate over a clock window and return a precise verdict (holds) plus a concrete witness/counterexample." It enumerates the five modes and the term/predicate structure, making the tool's unique role unmistakable among siblings like get_signal_at_time and search_signals. It also clarifies read-only scope with "Reads existing waveforms only."

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

Usage Guidelines4/5

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

The description gives a clear use case: "Use to prove/disprove an RTL inference in one call." It also provides mode-level guidance, e.g., implication as the protocol-response template, overlap=false for stability/hold properties, and sequence for address-stride checks. It does not explicitly name sibling alternatives or state when not to use this tool, so it stops short of a 5.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gokeshenzhen/TraceWeave'

If you have feedback or need assistance with the MCP directory API, please join our Discord server