Spawns a background LLM agent to handle a task. Checks RAM (needs 500MB+), enforces max 2 concurrent dispatches. Returns PID and log file path.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task description for the background agent. | |
| max_turns | No | Max turns for the agent. Default: 15. | |
| permissions | No | File paths the agent is allowed to edit (bypasses UNTOUCHABLE for these files). Expires after 24h. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no behavioral details beyond readOnly/openWorld/idempotent/destructive hints. The description adds key behaviors: spawning a background agent, checking RAM, concurrency limit, and return values (PID, log file path). No contradiction.
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?
Three sentences with no unnecessary words. Front-loaded with the core action, then key constraints, then return values. Every sentence adds value.
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 covers purpose, preconditions, resource limits, and output format (PID, log path). No missing essential details for a dispatch tool of this complexity.
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 baseline is 3. The description adds context: 'task description' for the task parameter, default 15 for max_turns, and expiration of 24h for permissions, providing meaning 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 clearly states the tool spawns a background LLM agent to handle a task, using a specific verb and resource. It distinguishes from sibling tools which are mostly audit/check tools, making this unique.
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 constraints (RAM needs 500MB+, max 2 concurrent dispatches) but does not explicitly state when to use vs alternatives or when not to use. Since siblings are very different, the constraints serve as implicit guidance.
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.
Most tools have clearly distinct purposes, but there is some overlap among multiple audit/check tools (e.g., accountability_check, drift_audit, security_audit). However, descriptions and naming help differentiate their specific scopes, so ambiguity is low.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., check_archive_safety, propagate_family_member), making them predictable and easy to understand.
33 tools is on the high side, but the server covers a broad domain (system health, audits, propagation, session management, etc.). The count is justified by the comprehensive scope, though it may feel heavy for agents.
The tool set covers the entire lifecycle of system management: health monitoring, audits, propagation, sessions, compliance, and more. No obvious gaps for the stated purpose of a nervous system framework.
