serial_read

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds meaningful context beyond them: a required capability flag and the fact that only the retained buffer tail is returned (implying older output is lost). It stops short of describing truncation/rotation behavior explicitly.

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?

Two sentences, no filler, with the purpose stated first and the gating condition immediately after. Every clause carries 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?

Has an output schema so return values needn't be explained, and the prerequisite is stated. But with 0% schema coverage on two parameters and no routing to sibling tools, an agent still has gaps before calling it confidently.

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% and the description never explains vm_name or tail_chars. The word "tail" hints at the truncation parameter's meaning, but its default of 32768 and the format/identity expectations for vm_name are left entirely to the schema's bare type declarations.

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?

Specific verb+resource: "Read the retained tail of an attached serial console." Scope (retained tail) is precise, so it's distinguishable from console_* siblings, though it doesn't explicitly contrast with serial_status or debug_serial_status.

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 one real precondition ("Requires ALLOW_DEBUGGER"), which is useful gating, but never says when to choose this over serial_status, debug_serial_status, or serial_connect, nor what happens without the flag.

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