causal_trace

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

With no annotations, the description fully covers behavioral traits: declares read-only, explains prerequisites, return value structure (ordered chain with confidence scores, solution or empty chain), and includes an example. No contradictions.

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?

Description is concisely structured with front-loaded purpose, clear sections for usage, requirements, return values, and alternatives. Every sentence adds value without redundancy.

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?

Despite no output schema, the description fully explains return values (ordered chain, confidence, solution, or empty chain with message). Context signals indicate no output schema, but the description compensates completely, including an example, making it complete for agent use.

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, but description adds significant meaning: clarifies 'problem', notes default for 'max_depth', explains 'tags' as optional narrowing, and provides a concrete example with syntax and output, greatly aiding agent 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 clearly states the tool performs root cause analysis by tracing causal chains from root to symptom and surfacing solutions. It uses specific verbs ('traces causal chain', 'surfaces solution') and distinguishes from siblings like 'recall_best_solution' and 'syndicate_search'.

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?

Explicitly states prerequisite ('brain must have lessons stored') and provides clear when-to-use vs. alternatives: 'Use recall_best_solution for direct topic lookup... causal_trace when you have a symptom and need the full root-cause chain'.

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