serial_read

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

With no annotations, the description carries the full burden and does well: it discloses non-blocking behavior, the three early-exit conditions, the return shape (text + HEX + match flag), and a side effect (content accumulates into the session log). It omits error/timeout failure behavior, which is the main remaining gap.

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?

Purpose and non-blocking qualifier are front-loaded, followed by tightly scoped one-line explanations of each parameter and the return format. No filler sentences; every clause adds information.

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 an output schema exists, the return description is a bonus rather than a necessity. The parameters, exit semantics, and side effect are all covered, leaving only prerequisite/error-handling details that an agent might want for a serial read.

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 description coverage is 0%, so the description must compensate, and it does: expect is explained as a regex with immediate return, idle_ms as a silence timeout, and seconds as the total duration cap, each with a concrete example. Only 'handle' is left unexplained, but its role is obvious from context.

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?

States a specific verb and resource ('从串口读取数据') plus a key behavioral qualifier (non-blocking, three early-exit conditions). An agent can distinguish it from serial_send/serial_open by the read semantics, though it never explicitly names those siblings.

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?

Implied usage is conveyed through the three exit conditions (expect/idle_ms/seconds), which tells the agent how the read terminates. However, there is no explicit when-to-use vs alternative guidance and no stated prerequisite that a serial_open handle is required first.

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