Ultrabrain Think

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behaviors beyond annotations: it is a reasoning gate, supports branching/revision, requires verification before concluding, and includes meta-checkpoints. Annotations only indicate non-readOnly and non-destructive, so the description adds critical transparency about how the tool modifies reasoning state.

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?

The description is a single, dense paragraph that front-loads purpose and immediately follows with actionable protocol. Every sentence earns its place, covering when to branch, revise, set next_thought_needed, and even ends with a meta-question. No redundancy or 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?

Given the tool's complexity (33 parameters, no output schema), the description provides a coherent protocol that guides usage across diverse reasoning scenarios. It covers branching, revision, quality metrics, and verification, but could mention the return value or side effects more explicitly.

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?

While schema coverage is 100%, the description adds semantic context by prescribing how parameters should be used (e.g., attach evidence for claims, set step_type honestly, adjust total_thoughts). This goes beyond per-parameter descriptions, providing a usage narrative that enhances parameter understanding.

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 explicitly states it is a 'Canonical LCV reasoning gate for code work, branching, revisions, quality metrics, bias checks, confidence, and meta checkpoints.' This clearly identifies the tool as the primary reasoning step tool, distinguishing it from sibling tools like ultrabrain_analyze or ultrabrain_review by covering all aspects of reasoning.

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 a detailed protocol: state evidence and assumptions before conclusions, set step_type honestly, attach evidence for factual claims, branch and revise appropriately, adjust total_thoughts, and only set next_thought_needed to false after verification. It explains when to use these features but does not explicitly exclude scenarios or compare to siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.