generate_mosfet_amplifier

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the gain formula, the auto-bias behavior based on VTO/KP, the consequence of mis-biasing (saturation drop and gain collapse), and the output being .CIR text. This is rich, non-obvious behavior that goes far beyond what the schema reveals.

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: a one-line summary, a compact paragraph of circuit behavior and key formulas, a bulleted Args list, and a return statement. Every sentence contributes substantive information, and the most important identifying information is front-loaded. No filler is present.

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?

The description is self-sufficient for a generator tool with 9 parameters and an output schema. It covers circuit topology, biasing strategy, gain expression, parameter semantics, and the return type. It even warns about a common failure mode (mis-biasing). Given the absence of annotations, this is a complete and robust description.

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 schema has 0% description coverage, forcing the description to compensate. The dedicated Args section defines every one of the 9 parameters, including domain-specific syntax (e.g., source as Micro-Cap value) and nuanced behavior (e.g., r1/r2 auto-bias when unset). This fully compensates for the sparse schema.

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 opens with a specific and informative statement: 'Draw a .CIR common-source MOSFET gain stage (NMOS primitive).' It names the exact circuit type and technology, distinguishing it clearly from sibling tools like generate_emitter_follower or generate_differential_pair.

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 provides context by specifying the circuit topology and bias scheme, and it suggests a downstream action ('Feed the result to simulate_schematic'). However, it does not explicitly state when to choose this tool over alternatives or when not to use it. No alternative tools are named, so guidance is mostly implicit.

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