finder_searchSearches for files by name anywhere on this Mac (uses mdfind/Spotlight); pass path= to scope it to one folder. Credential and identity locations are refused.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Limit search to this directory (optional) | |
| limit | No | Max results (default 50) | |
| query | Yes | Filename or content to search for |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | ||
| query | Yes | ||
| results | Yes |
Changes observed during successful MCP inspections.
Output schema / properties / results / items / properties / cloud_onlyAdded value: +{
+ "description": "Present and true when the file is only in iCloud/the cloud provider (not on disk)",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description adds useful behavioral context beyond that: it uses mdfind/Spotlight, searches globally unless path is supplied, and refuses credential/identity locations. It does not discuss performance or result limits, but the output schema covers return shape.
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 dense sentences, front-loaded with the core action and scope, then the path-scoping modifier and safety boundary. There is no filler.
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 read-only local file search with an output schema and clear annotations, the definition covers the essential operational context: search mechanism, scope, optional path narrowing, and refusal boundaries. The main omission is explicit routing versus sibling file-search tools.
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 100%, so all three parameters are already documented. The description reinforces path scoping, but it describes the query as searching by name while the schema says 'Filename or content', and it does not add syntax or behavior for limit or query matching beyond the schema.
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?
The description gives a specific verb and resource (searches for files), a clear scope (anywhere on this Mac), and implementation detail (mdfind/Spotlight). It does not explicitly distinguish this from close siblings such as file_search or finder_list, so it falls short of 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 description implies local Mac file search and mentions that path= can scope results to one folder, plus it states that credential and identity locations are refused. However, it does not explicitly say when to use this instead of file_search, finder_list, or cloud search siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.