read_memory

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

No annotations provided, so description bears full burden. It states the tool reads memory and returns JSON hex string, but does not disclose behavior on invalid addresses, side effects (though reading is non-destructive), connection requirements, or error handling. Adequate for a simple read but lacks depth.

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?

Description is brief with a one-line title, one-line explanation, and structured Args/Returns sections. Front-loaded with key verb and resource. No wasted words; every sentence earns its place.

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?

Given the tool's simplicity (2 params, read-only, output schema exists), the description covers the core behavior and return format. Missing details like error handling, alignment, or byte order, but these are minor for this domain. Sufficient for most use cases.

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?

Input schema has no property descriptions (0% coverage), but the description explains address as starting address with example (0x08000000) and size as byte count with range (1-1048576). This adds significant meaning beyond the schema's type-only definitions.

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 states '读取 MCU 内存' (read MCU memory) and '从目标 MCU 的指定地址读取内存数据' (read memory data from specified address of target MCU). It clearly identifies the verb (read) and resource (MCU memory), distinguishing it from sibling tools like write_memory (write) and read_rtt (RTT logging).

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?

No explicit guidance on when to use read_memory versus alternatives like read_rtt or get_device_info. The context is implied by reading raw memory at an address, but absence of when-not-to-use or prerequisites limits its helpfulness for agent decision-making.

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