check_jlc_orientation

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

Adds substantial behavior beyond the annotations: name-based pad matching with a geometry fallback, ambiguous matches flagged for human polarity confirmation, pin-function matching (K/A, FB/EN), permanent caching, and a 15 s inter-request throttle. One tension is that annotations declare openWorldHint=false while the description states fetch=true reaches easyeda.com over the internet; the fetch is bounded and cached, so it reads as a nuance rather than a hard contradiction.

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 core purpose is front-loaded in the first clause, and every later detail (matching strategy, ambiguity handling, caching, throttling) is informative rather than filler. It is dense and reads as a single sprawling sentence with nested parentheticals, which slightly hurts scanability.

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 no output schema, the description conveys that the result is a derived rotation/offset plus ambiguity flags, which is the key return concept. It covers the matching logic and network constraints adequately; only the `refs` scoping and the exact report shape remain implicit.

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%, so the description must carry parameter meaning. It documents `fetch` thoroughly (downloads missing footprints, cache behavior, rate limit), but never explains what `refs` does (default null implies all parts, but this is left to inference), so the compensation is only partial.

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: comparing each placed part's footprint against the JLCPCB-assigned footprint and deriving the CPL rotation/offset to align them. This is unambiguous and clearly separable from siblings like export_cpl or update_from_libraries.

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?

It explains the two operating modes (fetch=true downloads missing footprints; otherwise local cache only) and the 15 s rate limit, which is useful conditional context. However, it never states when an agent should run this relative to alternatives such as export_cpl, run_drc, or update_from_libraries, so the routing guidance is only implied.

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