madc_deliberate

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

With no annotations, the description carries full burden. It discloses triggers, the 6 agents, voting process, resolution storage, and the need for causal_trace on split votes. Could be improved by describing success/failure outcomes.

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 efficient and front-loads purpose. It contains all necessary information but could be slightly tighter. Still well-structured.

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 complexity and no output schema, the description explains input, process, outcomes, and next steps comprehensively. It covers all essential aspects for an AI agent to invoke correctly.

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?

Input schema has 100% coverage with descriptions. The description adds minimal extra meaning beyond the schema, e.g., the example topic 'fix:jwks-rotation'. 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?

Description clearly states it's a 'Multi-Agent Deliberation Chamber' for resolving conflicting lessons, names the 6 specialist agents, and explains the process. It differentiates from sibling 'causal_trace' by noting when that tool is needed.

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 'When conflicting lessons exist for a topic' and mentions it's called automatically by learn_from_attempts. Additionally, it provides guidance on when causal_trace is required (split vote). Missing explicit when-not-to-use scenarios beyond that.

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