brain_searchSearch your Brain files (your brains plus those shared with you) for a phrase; returns matching files with the surrounding lines so you can decide what to brain_get. Needs your agent bearer token.
| Name | Required | Description | Default |
|---|---|---|---|
| brain | No | Optional brain to search (owner-handle/name for shared brains). Omit to search all. | |
| query | Yes | Case-insensitive phrase to look for. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the full burden. It discloses the auth requirement ('Needs your agent bearer token'), the scope of files searched, and the return shape ('matching files with the surrounding lines'). For a read-style search tool, this is sufficient behavioral transparency.
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 with no filler. The core search behavior is front-loaded, the return value is explained with a practical purpose, and the auth requirement is stated plainly. Every sentence earns its place.
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?
The description is complete enough for a search tool with a simple schema and no output schema: it explains what is searched, what is returned, and what the agent needs to run it. Minor gaps like pagination or result limits would be useful, but they are not necessary for correct selection and invocation.
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?
The input schema already fully describes both parameters with 100% coverage. The description adds a little context about searching one's own and shared brains, but it does not meaningfully extend the parameter semantics beyond what the schema provides. Baseline 3 is appropriate.
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 clearly states a specific action ('Search your Brain files'), the resource scope ('your brains plus those shared with you'), and the outcome ('returns matching files with the surrounding lines'). It is easily distinguished from siblings like brain_get, brain_list, and brain_write.
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 provides clear context for when to use this tool: when searching across Brain files, with the explicit downstream suggestion 'so you can decide what to brain_get'. It does not explicitly contrast with search_skills, but the scoping to Brain files and the naming make the distinction clear enough.
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.
Each tool targets a distinct resource and action: Brain files are handled by brain_get/list/search/write, while skills are handled by get/install/search/submit_skill. Even the two 'get' tools differ clearly by resource type in their names and descriptions.
The Brain tools consistently use a noun_verb pattern (brain_get, brain_list, brain_search, brain_write), but the skill tools switch to verb_noun (get_skill, install_skill, search_skills, submit_skill). The mixed ordering is readable but not fully consistent across the tool set.
Eight tools is well-scoped for a server covering two related domains: personal Brain memory and skill catalog management. Each tool serves a clear purpose without redundancy or bloat.
The Brain domain covers list, get, search, and write, but lacks a delete/remove operation. The skill domain covers search, inspect, install, and submit, which supports the main workflows. Overall the surface is strong with only minor gaps.