Retrieve derived STM32 clock frequencies (HCLK/SYSCLK/PCLK) and RCC settings from a saved .ioc file plus live reads to verify clock-tree configuration.
Clock tree state: derived frequencies (HCLK/SYSCLK/PCLK/...) and the RCC settings that produce them, read from the saved .ioc plus live reads.
| Name | Required | Description | Default |
|---|---|---|---|
| params | No | Extra RCC parameter names to read live | |
| project_id | Yes | Project id |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, but it does add real signal: it discloses that data comes from the saved .ioc file merged with live reads, which tells the agent results may reflect unsaved state. However, it never states that the call is read-only/non-mutating, what happens if no project is open, or whether a live read requires device/IDE connectivity — meaningful gaps for a tool that mentions live access.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense sentence fragment with zero filler, and the core resource is front-loaded before the data-source clause. It loses a point only because the verbless phrasing makes the action slightly less immediate than an explicit 'Returns/Reads...'.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter read query with no output schema, the description does outline the return content (derived frequencies and RCC settings), which is useful. But it leaves the response shape, units, and the required preconditions for live reads unspecified, so an agent still cannot predict what it will get back or when the call would fail.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The phrase 'RCC settings that produce them' loosely maps to the optional params array of extra RCC parameter names, but the description adds no syntax, naming convention, or behavior beyond the schema's own 'Extra RCC parameter names to read live'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names the specific resource (clock tree state: derived HCLK/SYSCLK/PCLK frequencies plus the originating RCC settings) and its data sources (saved .ioc and live reads). It is a noun phrase rather than a verb+resource statement, and it never distinguishes itself from siblings like clock_set, clock_resolve, or clock_param_possible_values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to call this versus clock_set (the mutating counterpart) or clock_resolve/clock_param_possible_values, nor any stated prerequisite such as an open project or a connected target. The agent must infer all routing from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.