read_memory

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

No annotations are provided, so the description must carry full burden. It discloses maximum bytes (1024), default width (32), and return format (integer list and hex string). It does not mention read-only nature or prerequisites (e.g., connection required), but the read behavior is implied.

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 description is well-structured with a purpose line, address ranges for context, arg details, and returns. It is concise, front-loaded, and every sentence adds value. No fluff.

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 output schema exists (context signals), the description need not detail return structure. It covers all parameters, constraints, and usage hints. It could mention that a connection is required, but the sibling 'connect' implies it. Overall, it is sufficiently complete for an experienced user.

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 0%, meaning the schema provides no descriptions. The description adds full semantics: address as hex string, num_bytes max 1024 default 16, width options (8,16,32) with default 32 and explanation of what width means. This fully compensates for the schema gap.

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 clearly states '读取目标内存' (read target memory), specifying the verb and resource. It provides common address ranges for ARM Cortex-M, which helps define the tool's domain and distinguishes it from siblings like write_memory or read_registers.

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?

The description includes common address ranges (Flash, SRAM, peripherals, debug) that imply typical usage contexts. It does not explicitly state when to use vs. alternatives, but the examples guide appropriate use. Siblings like read_variable or read_rtt target higher-level constructs, so the memory address focus differentiates it.

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