find_model

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

Annotations declare readOnlyHint=true explicitly, and the description doesn't contradict that. It goes beyond annotations to disclose the WSL/LTspice path-format quirkchers, the port/params/device_type fields, and the warning about wiring order for .MODEL devices — valuable context for an agent. Minor gap: no mention of the default cutoff behavior or that results are ranked, but the fuzzy-matching and exact behavior are clearly described.

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 fairly long (≈200 words) but every sentence earns its place: fuzzy-matching behavior, exact mode, field semantics, WSL path nuance, and .MODEL vs subcircuit distinctions are all covered. It is front-loaded with the purpose and then expands into detail. Slightly dense, but not bloated — a solid 4.

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 a rich output schema and comprehensive annotations, the description exceeds the bar. It covers when to use fuzzy vs exact, what each returned field means, the WSL path context, and the critical usage gotcha (wiring .MODEL parts without node order). For a 7-parameter tool with high schema coverage monitored externally, this is complete.

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 coverage is already 100%, so the baseline is 3. However, the description adds significant value: it explains the *semantics* of the returned fields (ports, params, device_type, usage order string) and clarifies the behavioral meaning of parameters that the schema leaves implicit (e.g., exact=true bypasses fuzzy matching entirely, cutoff/limit ignored when exact=true, include_directive path format). This meaningfully surpasses the bar.

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 opening sentence states 'Find model/subcircuit candidates across loaded (and optionally built-in) libraries' with specific verbs and resource. It clearly distinguishes itself from siblings like list_components and list_libraries by focusing on search with fuzzy matching, exact mode, and returning candidates with metadata like include_directive and ports. The purpose is specific and unambiguous.

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 explicitly distinguishes between fuzzy and exact search, explains when to pass exact=true, and notes the tool folds in model_info behavior (`call find_model(name=X, exact=true, full=true)` for a single model's body). It also covers WSL-specific path behavior, implicitly guiding when a user might see unexpected paths. No explicit mention of alternatives, but the tool itself is clearly positioned as the search-plus-details hub.

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