Claude Debate Reply

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

With no annotations, the description carries the full burden. It discloses key behavioral traits: verification of evidence before rebutting, convergence criteria, and handling of result format (json vs prose). This goes beyond basic expectations and aids correct invocation.

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 well-structured, front-loading the core action and then providing step-by-step guidelines and a warning. Every sentence is informative without being verbose, earning 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?

Given the tool's complexity (multiple response actions, convergence logic, format handling) and no output schema, the description covers most necessary aspects. Minor gaps exist (e.g., error handling, structure of remaining_disputes), but overall it provides sufficient context for an agent to use the tool 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?

Schema coverage is 100%, providing descriptions for each parameter. The description adds workflow context (e.g., 'session_id from claude_debate_open or the previous debate round') and clarifies usage of the responses parameter ('Accept or rebut Claude's prior claims.'), enhancing understanding beyond the schema alone.

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 'Continue an open evidence debate' using a specific verb and resource. It distinguishes from siblings like claude_debate_open (which starts a debate) by focusing on continuation and accept/rebut actions.

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 explicit guidance on when to use the tool (to accept or rebut counter-claims) and includes convergence rules (stop when remaining_disputes empty or after three rounds). It does not list exclusions or alternative tools, but the context is clear given the sibling tools.

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