강의 노트 대상

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

Beyond the readOnlyHint and openWorldHint annotations, it discloses the confirmation-dialog flow, that only target selection occurs here, and that approved calls return readable files and save folders per week. It also clarifies that the note body is not produced here but saved later via save_notes.

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 purpose is front-loaded, followed by selection rules, return behavior, and the save_notes separation. Every sentence contributes operational or safety-relevant information without repetition.

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?

For a read-only target-selection tool with no output schema, the description covers why it is called, what it filters, how confirmation works, what is returned after approval, and how saving is handled separately. Nothing essential for correct invocation 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 description coverage is 100%, so the schema already documents week, course, confirmToken, and instructions. The description adds context about instruction changes and prompt-injection caution, but does not add syntax or per-parameter semantics beyond the 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 states a specific verb and resource: it selects which weekly lecture-note targets to build from saved materials and STT results. It clearly distinguishes itself from the sibling save_notes by saying the note body is written separately and stored via save_notes.

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 gives explicit selection rules: include weeks with no notes, changed materials, new STT, or changed instructions, and skip the rest. It also names save_notes as the separate saving step and mentions that video lectures lacking STT are reported by week.

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