Skip to main content
Glama
Sign In
naja-scope

naja-scope

by keplertech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

load_vhdl

Load VHDL design files into the active session to elaborate a two-state RTL subset, then query hierarchy, connectivity, and source references across the design.

Instructions

Load VHDL into the active session (beta, restricted two-state RTL subset). Prefer passing every file of the design as one list (any order; units are resolved across files). Single-file calls still work: load package files first, then the top. Package-only files or entities awaiting generics may return top=null. Use hierarchy, cards and connectivity queries on the elaborated design. Use get_source for entity, port, signal, instance and process source references. intent=True enables get_intent for enum literals, record fields, generics and symbolic ranges. Unsupported constructs may fail during beta development. Returns the top summary when elaborated, language and beta status.

Input Schema

NameRequiredDescriptionDefault
topNoTop entity name; omit to infer the top.
fileYesA local VHDL source path (.vhd/.vhdl), or a list of paths loaded as one batch in any order.
intentNoRetain VHDL source intent for get_intent; the last load_vhdl call decides whether it stays live.
libraryNoVHDL library the files compile into, for designs that name it, as in `library neorv32;`. Omit for designs that use `work`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.23
    • addedInput schema / properties / intent
      Added value: +{
+  "default": false,
+  "description": "Retain VHDL source intent for get_intent; the last load_vhdl call decides whether it stays live.",
+  "title": "Intent",
+  "type": "boolean"
+}
    • addedInput schema / properties / library
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "VHDL library the files compile into, for designs that name it, as in `library neorv32;`. Omit for designs that use `work`.",
+  "title": "Library"
+}
  2. Changed3 schema fields changed
    • addedInput schema / properties / file / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]
    • changedInput schema / properties / file / description
      Previous value: -"One local VHDL source file path (.vhd or .vhdl)."New value: +"A local VHDL source path (.vhd/.vhdl), or a list of paths loaded as one batch in any order."
    • removedInput schema / properties / file / type
      Removed value: -"string"
  3. Addedv0.1.9

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and idempotentHint=false; the description adds real context beyond that, warning that unsupported constructs may fail during beta and that package-only files or uninstantiated entities may yield top=null. It also discloses statefulness semantics for the intent flag (the last call decides whether intent stays live) and that a top summary is returned. It does not say whether a new load replaces or accumulates prior session contents.

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 primary action and the beta caveat, then structured as short directive sentences. A few lines (the top=null case, the intent live/dead note) are dense but each carries operational value, so little is wasted.

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?

No output schema exists, and the description compensates by stating that the top summary plus language and beta status are returned. Combined with the failure-mode and null-top notes, an agent has enough to call this correctly; only the session-replacement semantics remain unspecified.

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 100%, so the schema already documents all four parameters, and the description largely restates them. It adds marginal meaning — batch ordering is irrelevant because units resolve across files, and intent controls get_intent availability — which is useful but thin beyond the baseline for full schema coverage.

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?

Opens with a specific verb and resource ("Load VHDL into the active session") plus the qualifier "beta, restricted two-state RTL subset," which tells an agent exactly the scope of accepted input. It also names the downstream tools (hierarchy, cards, connectivity, get_source, get_intent), so the agent can position this load step relative to siblings without opening another schema.

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?

Gives explicit calling strategy: prefer one batched list in any order, or for single-file calls load package files before the top. It also routes follow-up work to the right tools. The only gap is that it never states when NOT to use it (e.g., use load_verilog/load_systemverilog for those languages), which matters given the sibling loader tools.

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

Deploy Server

Other Tools