LMS 강의자료 동기화

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

Goes well beyond the annotations: incremental sync semantics (only new/changed files), no overwriting of user-edited files, no deletion of files that vanished from LMS (reported as removed), a per-call download cap with resumable pagination via `more`, and an explicit prompt-injection warning that course/file names are data not instructions. readOnlyHint=false is consistent with writing files to local disk, and destructiveHint=false is reinforced by the no-overwrite/no-delete guarantees.

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?

Front-loads what it downloads and where, then layers safety guarantees, pagination, and the injection caveat. Every sentence carries distinct operational information with no filler.

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?

An output schema exists, so return shape needn't be re-explained, yet the description still surfaces the key return signals (`removed`, `more`, local path). For a single-optional-param sync tool, nothing an agent needs in order to call it correctly is missing.

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 100%, so the `course` substring filter is already documented; the description adds scope meaning the schema lacks by explaining that the target set is gated by the tracked-course setting from set_course_tracking. It does not restate the case-insensitive substring matching, but the schema carries that.

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 (download/sync), a specific resource (LMS lecture materials: file and folder modules), the exact destination path template, and the return value (local path). This is clearly distinct from siblings like delete_materials, read_material, and list_courses.

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 concrete operating context: target courses follow set_course_tracking, and if `more` is true the agent should call again to continue. It does not explicitly name when to prefer this over read_material or list_courses, so it stops short of full when/when-not routing.

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