Skip to main content
Glama
ltspace

dowse

by ltspace
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

search

Read-only

Find files and contents in a local index using filters like path, modification date, size, and keyword exclusions. Returns highlighted hits for quick candidate review.

Instructions

在本地全文索引里搜索，返回命中列表；命中词用 «» 标出。查询串支持内联操作符：path:关键词（按路径）、mtime:>2026-01-01 / mtime:<=2026-07（按修改日期，比较符 > >= < <=，日期 YYYY-MM-DD 或 YYYY-MM）、size:>10mb / size:<500kb（按体积，单位 kb/mb/gb）、大写 OR 分组（组内空格为 AND）、-词 或 NOT 词 排除；带空格的操作数加引号如 path:"我的 文档"。默认按相关度排序，可用 sort 改按修改时间/体积排；ext 可按扩展名过滤（逗号分隔多个）；limit/offset 翻页，返回里的 total_hits 是匹配总数。先用这个工具定位候选文件，再用 preview 看更长的上下文。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
extNo只保留这些扩展名的结果（不含点）。逗号分隔可给多个，如 "md" 或 "md,pdf,txt"； 不需要按扩展名过滤就整个字段别传（传空串或纯逗号会报参数错误）
sortNo排序方式：relevance（默认，按相关度）/ mtime（按修改时间，新的在前）/ size（按体积，大的在前）。非 relevance 排序下 BM25 分数没有意义，结果里 不返回 score 字段。传其它值会报参数错误
limitNo最多返回几条，默认 10；和 offset 搭配翻页
queryYes查询词，支持空格分隔多个词（AND 语义）和 "短语查询"。也支持内联操作符： `path:关键词`（按路径匹配）、`mtime:>2026-01-01`/`mtime:<=2026-07`（按修改 日期，支持 > >= < <=，日期写 YYYY-MM-DD 或 YYYY-MM）、`size:>10mb`/`size:<500kb` （按体积，单位 kb/mb/gb）、`A OR B`（大写 OR 分组，组内空格是 AND）、 `-词` 或 `NOT 词`（排除）。带空格的操作数加引号，如 `path:"我的 文档"`
offsetNo跳过前多少条命中再取，默认 0；和 limit 搭配翻页（取第 2 页就传 offset=limit）。 返回里的 total_hits 是匹配总数，offset + 本页条数 < total_hits 就说明后面还有

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.1.0
    • changedInput schema / properties / ext / description
      Previous value: -"只保留该扩展名的结果（不含点，如 \"md\"、\"pdf\"），可选"New value: +"只保留这些扩展名的结果（不含点）。逗号分隔可给多个，如 \"md\" 或 \"md,pdf,txt\"；\n不需要按扩展名过滤就整个字段别传（传空串或纯逗号会报参数错误）"
    • changedInput schema / properties / limit / description
      Previous value: -"最多返回几条，默认 10"New value: +"最多返回几条，默认 10；和 offset 搭配翻页"
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "跳过前多少条命中再取，默认 0；和 limit 搭配翻页（取第 2 页就传 offset=limit）。\n返回里的 total_hits 是匹配总数，offset + 本页条数 < total_hits 就说明后面还有",
+  "format": "uint",
+  "minimum": 0,
+  "type": [
+    "integer",
+    "null"
+  ]
+}
    • changedInput schema / properties / query / description
      Previous value: -"查询词，支持空格分隔多个词（AND 语义）和 \"短语查询\""New value: +"查询词，支持空格分隔多个词（AND 语义）和 \"短语查询\"。也支持内联操作符：\n`path:关键词`（按路径匹配）、`mtime:>2026-01-01`/`mtime:<=2026-07`（按修改\n日期，支持 > >= < <=，日期写 YYYY-MM-DD 或 YYYY-MM）、`size:>10mb`/`size:<500kb`\n（按体积，单位 kb/mb/gb）、`A OR B`（大写 OR 分组，组内空格是 AND）、\n`-词` 或 `NOT 词`（排除）。带空格的操作数加引号，如 `path:\"我的 文档\"`"
    • addedInput schema / properties / sort
      Added value: +{
+  "description": "排序方式：relevance（默认，按相关度）/ mtime（按修改时间，新的在前）/\nsize（按体积，大的在前）。非 relevance 排序下 BM25 分数没有意义，结果里\n不返回 score 字段。传其它值会报参数错误",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  2. First observedv0.8.2

TDQS

A4.1/5.0
Behavior4/5

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

Annotations provide only readOnlyHint=true and a title. The description adds valuable behavior beyond that: BM25 score is suppressed for non-relevance sorts, ext with empty string or pure comma triggers a parameter error, invalid sort values error out, and total_hits reflects the total match count for pagination. These error conditions and output nuances are exactly the kind of context the readOnly annotation does not carry.

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 description is a dense single paragraph, but every clause earns its place given the tool's complex inline query language (path:, mtime:, size:, OR/NOT, quoting). Purpose is front-loaded and usage guidance is placed at the end. It could be better structured with line breaks or bullets for the operator list, but the density is justified by complexity.

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

Completeness4/5

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

With no output schema, the description must explain return behavior itself, and it does: hit list with «» markers, total_hits for pagination, and score suppression rules. The query language, filters, sort, and pagination are all covered. A minor gap is that the per-hit field structure is not described beyond the marker and score, but for a 5-param tool this is near-complete.

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

Parameters3/5

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

Schema description coverage is 100% with rich per-parameter documentation (query operator syntax, ext comma rules, sort semantics, limit/offset defaults, offset pagination example). The description largely restates the query operator syntax already present in the schema, adding little new parameter meaning. Per the baseline, 3 is appropriate when the schema does the heavy lifting.

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?

The description opens with a specific verb and resource: '在本地全文索引里搜索，返回命中列表' (search in local full-text index, return hit list). It names the hit-marking behavior with «» and explicitly differentiates from the preview sibling at the end, telling the agent search is for locating candidates first. Purpose is unambiguous and distinguishes from both siblings.

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?

The closing line '先用这个工具定位候选文件，再用 preview 看更长的上下文' (use this tool first to locate candidates, then preview for longer context) gives explicit workflow guidance relative to the preview sibling. However, it does not address the index_status sibling at all, so the when/not-when guidance is incomplete across the full sibling set.

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

Deploy Server

Other Tools