Skip to main content
Glama

cubemx1_probe_describe

Queries STM32CubeMX device, IP, pin, board, peripheral, and clock data offline to retrieve modes, parameters, candidate pins, and clock topology without launching CubeMX.

Instructions

Offline queries. kind=describe: device/IP definitions (modes, parameters, types and ranges, candidate values, owning RefMode and conditions, true/false/unknown under the current target), pin candidates. kind=boards/board: official ST boards (details include the seed base configuration and native BSP definitions); with board, queries and compilation share the same board context and board-level instances (instance name = board name) are queryable. kind=peripherals: every peripheral/middleware instance the device declares (with the IP type from its modes file). kind=pins: one IP's signals and their candidate pins in both directions, and with mode the leaf mode's required signals, candidate pins, must-be-explicit signals and conflicts; without mode it gives a per-mode summary. kind=clock: the device's clock topology as a graph, the upstream of one readout (view=upstream, all MUX branches and the fractional input kept), or the original clock-definition XML / one element fragment (view=raw). The clock views keep RAW facts separate from interpretation: every attribute, every condition, document order, all candidates of an ambiguous reference. Does not start CubeMX and does not solve any frequency.

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": "cubemx1_probe_describe"
  }
}

Input Schema

NameRequiredDescriptionDefault
ipNoinstance name, for example USART1; a board-level instance is the board name (with board)
seqNoraw record id (kind=clock, view=raw of one element)
kindNoquery kind, defaults to describe
modeNoleaf mode name (kind=pins) or a group name; leave out for a per-mode summary
sizeNopage size of a clock view; the payload reports what was left out
treeNoclock tree name override (kind=clock)
viewNoclock view, defaults to graph
boardNoboard id (name@revision@vendor) or board name; for describe it is the board context / BSP definition source
limitNomaximum number of entries for boards, defaults to 50
deviceNodevice RefName, for example STM32F103C(8-B)Tx
outputNoclock readout parameter name (for example HCLKFreq_Value) or element id; required for kind=clock, view=upstream
targetNotarget JSON (optional)
keywordNokeyword for boards, for example NUCLEO

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries substantial behavioral burden: it declares the tool is offline, does not start CubeMX, does not solve frequency, preserves raw clock facts separately from interpretation, reports omitted clock-view entries, and reuses board context for queries and compilation. It still does not describe error behavior or a full response envelope, but the key behavioral traits are disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and essentially one long paragraph with semicolon-separated mode clauses, which makes it harder to scan than a structured list would be. Most content earns its place, but the run-on format and mismatch between enum order and description order reduce clarity.

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?

For a complex 13-parameter, multi-kind tool with no output schema, the description covers what each kind returns conceptually and clarifies important constraints such as default kind, default clock view, board context, and clock paging. Remaining gaps, such as exact response shape or error handling, are minor relative to the kind-specific coverage provided.

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 the baseline is 3, but the description adds meaning beyond the schema by explaining kind-specific interactions: kind=pins changes output depending on mode, kind=clock view=upstream requires output, and board context affects queryable board-level instances. It does not add much for parameters like seq, tree, or target, but it meaningfully clarifies the important combinations.

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?

The description states that this is an offline query tool and enumerates the query kinds: device/IP definitions, boards, peripherals, pins, and clock topology. That is specific enough to distinguish it from build/generate/import/status siblings, although the umbrella phrase 'Offline queries' is broad and no sibling is named directly.

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?

It gives clear context for using each kind, including conditional behavior such as kind=pins with or without mode, and kind=clock with view=upstream or view=raw. It also says what the tool does not do ('Does not start CubeMX and does not solve any frequency'), but it does not explicitly name alternative sibling tools or state when not to use this tool.

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