MCP Agent Debate

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

Annotations already declare the safety profile (readOnly, non-destructive, idempotent, closed-world), so the description's real contribution is the operational metadata: the POST endpoint, cost of 100 credits at Tier 4, and the required fields. That cost signal is genuinely useful. What it omits is what agentA/agentB actually are, whether the debate consumes chart data, and the output shape, so it stops short of a rich behavioural picture.

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 prose is a single front-loaded sentence with zero padding, and the bracketed metadata is scannable. The metadata block is a bit blocky in token terms, but each line (endpoint, required fields, cost) carries distinct information.

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?

For a 6-parameter tool with a nested object and a cost-bearing LLM call, the description is thin: it does not explain the role of the chart parameter, the meaning of agentA/agentB, or the rounds/language knobs. The output schema relieves it of return-value duty and the cost line is a plus, but the input semantics gap leaves it incomplete.

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 description coverage is only 17%, so the description must compensate and it largely doesn't. It restates the three required names but never clarifies whether agentA/agentB are persona labels, model identifiers, or free-text instructions, and says nothing about rounds, language, or why a nested chart object is accepted. The critical ambiguity of the tool's main inputs is unresolved.

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 gives a concrete verb and resource: two personas debate a given topic and produce a multi-round transcript. That is enough to tell it apart from the bulk of the astrology catalogue, though it doesn't explicitly distinguish it from near-neighbours like astroway_mcp_multi_agent_coordinate or astroway_mcp_ai_chat.

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 only lists required fields; it never says when to choose this over agent_pool_status, multi_agent_coordinate, ai_chat or ai_comparison_coach, nor any precondition such as whether the agents must already exist in the pool. An agent is left to infer the routing decision.

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