Scan _Inbox files with short content previews to triage each item, decide its category and name, then move all selected notes in one batch.
List files in _Inbox with a short content preview for triage.
Decide a category and a name for each, then move them all with ONE
:func:kb_organize call. Returns at most limit items per call.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| preview_chars | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral load. It does disclose a real constraint — 'Returns at most ``limit`` items per call' — signaling truncation and the need to page. But it never explicitly declares the read-only nature, what previews look like when truncated, or whether subdirectories appear; for an unannotated tool that leaves meaningful gaps.
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?
Two short sentences with the capability front-loaded and the follow-up action second; nothing is padded. Slightly compressed formatting (docstring line breaks) costs it a point.
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 described, and the description covers purpose, triage pattern, and the downstream batch call. Missing only edge-case behavior (empty inbox, truncated previews, non-file entries) for full completeness.
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 0%, so the description must compensate for two undocumented params. It explains `limit` semantically ('at most limit items per call') and implies `preview_chars` via 'short content preview', but never names or bounds the preview parameter. Partial compensation only.
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 (list) plus resource (files in `_Inbox`) and the differentiating trait (short content preview for triage), which separates it from generic siblings like kb_list_tree and kb_search. It stops short of naming an alternative outright, so a 4 rather than a 5.
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?
The second sentence gives an explicit workflow: decide category and name per item, then batch the moves with ONE kb_organize call. That tells the agent both what this tool is for and which sibling to invoke next. It does not state when *not* to use it (e.g. for files outside _Inbox), so not a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.