강의 노트 저장

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

Annotations already flag destructiveHint=true, but the description adds crucial scoping: it only overwrites its own note files, never same-named files it did not write, and requires replace for existing notes. It also discloses the side effect of recording material fingerprints and instructions for later change detection. Return behavior and failure modes are still unstated, so not a 5.

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 action and destination, then the overwrite policy. The nested parentheticals add density but each clause carries real behavioral information; no filler sentences.

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 mutating write tool with no output schema, the description covers destination, overwrite policy, and the change-detection side effect well. It does not indicate what the tool returns or what happens on failure, leaving a modest gap.

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% and each parameter already documents its meaning, including replace and instructions. The description restates the replace semantics and the dir provenance without adding new format or constraint detail, so the baseline 3 applies.

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 (writes note-<week>.md) plus the exact destination (the week folder returned by list_notes), and notes the metadata side effect. An agent can distinguish this from save_summary and other siblings without opening the 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?

Makes the prerequisite explicit — dir must come from list_notes — and gates overwrites on replace: true only after user confirmation. It lacks an explicit when-not-here-use-X alternative against close siblings like save_summary, which keeps it below a 5.

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