start_searchInitiate a progressive search for files by name or across file contents, with options for path, patterns, case sensitivity, and result limits.
Start a progressive file-name or file-content search.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | . | |
| pattern | Yes | ||
| deviceId | No | ||
| deviceName | No | ||
| ignoreCase | No | ||
| maxResults | No | ||
| searchType | No | files | |
| timeout_ms | No | ||
| filePattern | No | ||
| contextLines | No | ||
| includeHidden | No | ||
| literalSearch | No | ||
| earlyTermination | No |
Changes observed during successful MCP inspections.
v0.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. Beyond that the description adds only the ambiguous word 'progressive' and discloses nothing about the async lifecycle, result retrieval, early termination, or timeouts, despite a timeout_ms parameter implying long-running behavior.
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, but this is under-specification rather than conciseness. The sentence is front-loaded with the verb, yet it omits information essential for a 13-parameter tool.
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 tool with 13 parameters, zero schema descriptions, no output schema, and an implied async/progressive result flow, one sentence is not sufficient. The agent cannot know how to retrieve results or when the search terminates.
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% across 13 parameters, so the description carries the full burden and fails it. It hints at two search modes but says nothing about pattern, path, contextLines, maxResults, filePattern, includeHidden, literalSearch, or earlyTermination.
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 ('Start ... search') and distinguishes two modes, file-name vs file-content, which maps to the searchType enum. However, it does not differentiate itself from closely related siblings such as stop_search, get_more_search_results, or list_searches.
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?
No when-to-use guidance and no alternatives named. The word 'progressive' implies an async/multi-step flow, but the description never tells the agent to poll get_more_search_results or how to stop via stop_search, which is exactly the routing information an agent needs here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.