consult_contrarian

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

With no annotations, the description carries the full burden. It discloses that this makes a direct query to a named external model and describes the nature of the analysis (adversarial, edge-case, race-condition checks). However, it does not mention return format, potential latency/cost of an LLM call, or whether state is modified, leaving some important behavioral context unspecified.

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, front-loaded sentence that names the action, the resource, and the outcome. There is no filler or repetition; every phrase earns 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?

For a 4-parameter tool with no annotations and no output schema, the description is somewhat thin. It makes the purpose clear and the schema documents parameters, but it does not explain the response shape or provide explicit usage boundaries relative to siblings. Adequate, but with clear gaps an agent must fill by inference.

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%—every parameter has a description, including the enum values for effort and the semantics of prompt and context. The tool description adds high-level purpose context but no parameter-specific detail beyond what the schema already provides, so the baseline of 3 applies.

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 uses a specific verb ('queries') plus a named resource ('The Contrarian (DeepSeek-V4 Pro)') and a concrete set of purposes (adversarial code review, bug-hunting, edge cases, race conditions, over-engineering checks). This clearly differentiates it from siblings like consult_architect or deliberate_council, which imply different consultation modes.

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 implies when to use the tool—when adversarial critique or bug-hunting is needed—but it never explicitly states when not to use it or names alternatives. Sibling names suggest different roles (e.g., architect vs. contrarian), yet the description leaves that routing entirely to inference.

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