Lists peripheral modes for an STM32CubeMX project, letting you inspect available MCU capabilities, all leaf modes, or currently mapped modes.
Peripheral modes: available (what the MCU can do), all (every leaf mode) or mapped (what is currently enabled).
| Name | Required | Description | Default |
|---|---|---|---|
| which | No | Selection | mapped |
| peripheral | No | Peripheral regex (USART.* , .*) | |
| 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?
No annotations are present, so the description must carry the behavioral burden. It explains what the option values return but does not state that the operation is read-only, does not mention side effects, permissions, or output structure, and leaves required project context to the schema.
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?
The single sentence is tightly scoped, front-loads the resource ('Peripheral modes'), and spends its words only on the three enum meanings. No redundant restatement of schema or annotations.
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 simple three-parameter list tool with full schema coverage and no output schema, the description covers the key `which` semantics. It is still incomplete for tool selection because it does not clarify read-only behavior or how it differs from `mode_catalog`, `sub_modes`, or `mode_check`.
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 a baseline of 3 is warranted, and the description adds meaningful semantics for `which` by defining `available`, `all`, and `mapped` beyond the schema's terse 'Selection'. It does not elaborate on `peripheral` or `project_id`, but those already have schema descriptions.
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 identifies peripheral modes and explains three selection categories, but it never states an explicit action such as 'list' or 'return' and does not distinguish this tool from siblings like mode_catalog or sub_modes. The agent can infer a read/list purpose from the name and text, but the description itself is category-focused rather than purpose-focused.
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?
It maps each `which` option to a use case (`available` = MCU capability, `all` = every leaf mode, `mapped` = currently enabled), giving implied guidance for selecting a mode set. However it says nothing about when to call mode_list versus sibling tools, nor about prerequisites such as `project_id`.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.