핵심 요약 대상

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

Goes well beyond the readOnly/openWorld annotations: it discloses the user confirmation window, the per-scope (one file per course/week-range) granularity, the skip logic, that weeks without notes are surfaced, and what is returned after approval (notes to read plus storage folder). It also warns that course names and note contents are LMS data, not instructions — a prompt-injection caveat no annotation conveys.

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-loaded with the purpose, then selection rules, then return behavior, then the injection caveat — a sensible order with no filler. It is dense but every sentence carries information; slightly more compact phrasing could improve it.

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 steps in to describe the return (target list shown for confirmation, then per-course notes and storage folder on approval) and the confirmToken fallback is covered by the schema. A precise return shape would be helpful but the agent has enough to call it correctly.

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 parameter meanings are already documented; the description still adds value by tying `instructions` to re-selection behavior (a changed instruction makes a target eligible again) and framing course/week params as a scope unit that yields exactly one summary file. It stops short of explaining the confirmToken fallback flow in prose.

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 (고른다/selects) and a specific resource (per-course/week core summary targets) derived from notes created by save_notes, and explicitly hands off writing to save_summary. An agent can distinguish it from list_notes and save_summary without opening any schema.

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 spells out the selection predicate precisely: pick targets with no summary, changed notes, or changed instructions, and skip everything else, plus report weeks lacking notes. Sibling routing is implied through save_notes (input) and save_summary (output) rather than naming alternatives explicitly, which keeps it just short of a 5.

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