knowledge-base

stale_notes

Lists notes requiring revalidation due to changed code references or age, letting you filter by reason. Prioritize verification workflow with actionable queue.

Instructions

재검증이 필요한 노트 큐 — 대시보드 '재검증 큐'와 동일한 기준·순서. 참조 코드(code_refs)가 그 후 변경된 노트(reason='code' — 지금 틀렸을 수 있어 급함)가 먼저, 마지막 검증이 days일 이상 지난 노트(reason='age')가 그다음. superseded 노트는 제외. reason 파라미터('code'|'age')로 사유를 좁힐 수 있다.

재검증 워크플로: 각 항목을 get_document로 열어 내용(특히 stale_refs에 적힌 파일)을 현재 코드와 대조하라 → 여전히 정확하면 verify_note(document_id), 세부만 낡았으면 같은 title로 record_* 재기록(멱등 갱신), 결론이 뒤집혔으면 새 기록 + supersedes. 확신이 없으면 건드리지 말 것 — 잘못된 '검증됨' 표시는 미검증보다 해롭다. project가 자기 프로젝트와 다른 노트는 그 프로젝트의 코드 기준으로만 판정할 수 있으니 함부로 수정하지 마라. counts는 큐 전체 규모다 — results가 limit에 잘려도 남은 양을 알 수 있다.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`days`	No
`limit`	No
`reason`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 7, 2026

TDQS

A4.5/5.0

Behavior4/5

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

No annotations are present, so the description carries the full burden. It discloses ordering, superseded exclusion, counts semantics, and cautions about cross-project modifications. It stops short of explicitly stating whether the tool is read-only, but the behavior is otherwise well documented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is stated concisely, followed by workflow and safety guidance. It is longer than strictly necessary, but each section adds operational value and the structure is clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is comprehensive for a list-returning tool: it covers parameters, ordering, result semantics, workflow, and cautionary notes. Since an output schema is present, detailed return value documentation is not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite zero schema coverage, the description explains days as the staleness threshold, reason as a 'code'|'age' filter, and limit as a truncation boundary. All three parameters receive meaningful semantic description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States it returns a queue of notes needing re-verification, with explicit ordering and filter criteria. This clearly distinguishes it from sibling tools like search_code, get_document, and verify_note.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a clear re-verification workflow and explains when to use the reason filter. It does not explicitly contrast with alternative tools, but the operational context is strong enough for an agent to choose this tool appropriately.

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

Deploy Server