coldplunge.critique

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the nature of the critique (red-team, structured, focusing on unsupported claims, logical gaps, and edge cases), which gives the agent a realistic expectation of the output. It does not describe side effects, but as a critique tool it implies a read-only analysis, and the description adds meaningful context beyond the bare function.

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, focused sentence that front-loads the action and outcome. It is concise with no filler, and every word contributes to understanding the tool's purpose and behavior.

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?

The tool has a moderate complexity (nested arguments object, output schema present), but the description is thin on input formatting rules. It tells the agent what to submit but not how to structure the arguments inside the generic schema. The existence of an output schema reduces the need to explain return values, but the lack of parameter semantics makes the description only partially complete for a robust call.

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?

The input schema is a generic 'arguments' object with additionalProperties true and 0% documentation coverage. The description mentions what to submit (draft answer, plan, reasoning) but does not explain the expected structure, key names, or how to format the input. This leaves the agent with insufficient guidance on constructing a valid call, so the description fails to compensate for the schema's lack of detail.

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's function: it submits a draft answer, plan, or reasoning and returns a structured red-team critique. The verb 'submit' and the specific output ('critique: unsupported claims, logical gaps, and missed edge cases') make the purpose unmistakable. It also distinguishes itself from sibling tools like 'spa.feedback' and 'rest.relax' by explicitly focusing on adversarial review of drafts.

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 gives clear context by specifying the acceptable inputs ('draft answer, plan, or reasoning'), which tells the agent when to use it. However, it does not explicitly mention when not to use it or point to alternative tools (e.g., 'spa.feedback'), so it falls slightly short of a 5.

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