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 only states the return of the CIR and an explanation, but does not disclose side effects, error handling, idempotency, or any operational nuances. The description is minimal and lacks behavioral depth.

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 brief—two sentences—and front-loads the core purpose. It contains no fluff, though the phrase 'natural-language' appears twice, which is a minor redundancy. Still, it is efficient and 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?

The tool has four optional parameters with zero schema descriptions and no guidance on which to use, making it incomplete for an agent to call correctly. The output schema exists but its content isn't described; the description only mentions the return of CIR and explanation. Given the parameter ambiguity, the description does not provide enough context for proper usage.

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 schema has 0% description coverage, and the description does not clarify the meaning of the four parameters (text, prompt, task_text, description). It says 'natural-language task text' but does not specify which parameter receives it, leaving the agent unable to correctly populate inputs. The description fails to compensate for the schema's silence.

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: convert natural-language task text into CIR and a task_structure dict. It names a specific verb and resource, making the purpose evident. However, it does not differentiate this tool from siblings like cognitive.identify_task or cognitive.resolve_intent, so it lacks explicit sibling distinction.

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 phrase 'Every natural-language input is normalized into CIR before reasoning' implies the tool is a preprocessing step, giving context on when to use it (before reasoning). But it doesn't explicitly mention when not to use it or point to alternative tools, leaving the usage guideline somewhat implicit.

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