Serial Expect

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

The readOnlyHint annotation already covers the safety profile, and the description adds a useful behavioral cue by saying the tool 'waits' and has a timeout. It does not disclose whether pattern matching is regex or literal, whether caseSensitive defaults to false, or whether the session cursor advances, but the annotation lowers the burden for basic side-effect transparency.

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 a single, front-loaded sentence with no filler or redundancy. It efficiently captures the core behavior without wasting tokens, which is ideal for quick agent scanning.

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?

With five parameters, only 20% schema coverage, and important behavioral details like pattern matching semantics and case-sensitivity defaults unstated, the one-sentence description is not enough for fully confident invocation in non-trivial cases. The output schema and readOnlyHint help, but an agent would still need to guess at several edge behaviors.

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 only 20%, so the description needed to compensate by explaining pattern semantics, timeout units/defaults, fromOffset behavior, and caseSensitive meaning. Instead, it mostly paraphrases 'string pattern' and 'timeout', adding little beyond the schema's existing parameter names and the one fromOffset description.

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 a specific action ('wait for'), a concrete target resource ('string pattern in a serial session buffer'), and a limiting condition ('with timeout'). The verb 'wait for' clearly separates it from sibling tools like serial_read and read_serial_snapshot, so the tool's role is immediately identifiable.

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 implies when to use the tool: when you need to wait for a pattern rather than just read available data. However, it does not explicitly name alternatives, contrast behavior with serial_read/read_serial_snapshot, or state when not to use it, leaving the guidance to inference.

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