searchSearch a closed document collection using full-text queries to locate the exact files a filing step needs. Provide a collection path and query to retrieve matching records.
Full-text search in a closed collection.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| query | Yes |
Changes observed during successful MCP inspections.
v0.1.1Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "items": {
- "additionalProperties": true,
- "type": "object"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "searchOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds only the vague scope phrase 'closed collection' and says nothing about matching semantics, result ordering, pagination, or what 'closed' implies access-wise.
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?
A single short sentence with no wasted words, and the operation is front-loaded. The brevity is efficient, though it reflects under-specification rather than complete precision.
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 two-parameter search tool with no parameter descriptions and no output schema, the description should carry more weight. It does not explain the parameters, expected results, or how 'closed collection' scoping affects the search.
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 description coverage is 0%, and both parameters are required. The description does not explain what 'path' refers to (a collection root? a document?) or what query syntax is accepted, leaving a significant gap the schema cannot fill.
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 operation ('full-text search'), so the core purpose is identifiable. However, 'in a closed collection' is undefined, and the description never distinguishes this from search-adjacent siblings such as find_similar, find_duplicates, or survey.
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?
There is no guidance on when to use this versus list_folder, read_document, find_similar, or the other search-like siblings. The agent must infer that 'search' is the full-text entry point from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.