serial_read

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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely non-obvious behavior beyond them: it consumes/drains the buffer, is lossy across turns, and does not transmit on the port. It omits return formatting and empty-buffer behavior, which is why it is not a 5.

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?

Three tight clauses, zero filler, and the core action plus its main caveat ('lossy across turns') are front-loaded before the alternative-tool pointers.

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 no-param, fully annotated read tool with no output schema, the description covers purpose, consumption semantics, and alternatives. Only minor operational details (empty-buffer result, encoding/format of drained output) are absent.

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?

The tool takes zero parameters, so the baseline of 4 applies and there is no schema coverage gap to compensate for. The description adds no parameter detail, but none is needed.

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 ('drain the output this MCP session buffered since the last read') plus the critical scope qualifier 'without sending'. It immediately differentiates itself from siblings by naming what it is not (lossless history, text-waiting).

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?

Gives explicit when-to-use ('Quick look after your own command'), an explicit limitation ('lossy across turns'), and routes to the two correct alternatives by name with the parameter that selects them ('serial_output_history with since_seq', 'serial_wait_for'). Nothing is left to inference.

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