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

With no annotations, the description carries the full burden. It reveals that the tool makes a selection based on EVC but does not disclose side effects, state changes, required context, or what the output represents. For a tool that might influence compute resource allocation, this is a notable gap.

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?

A single front-loaded sentence with a useful label ('Adaptive compute budgeting:') and minimal waste. It loses a point for relying on unexplained acronyms within that sentence.

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 tool with a required nested object parameter, 0% schema coverage, and no annotations, the description is far too thin. Even though an output schema exists, the agent lacks enough context about inputs and criteria to invoke 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 description coverage is 0%, and the description does not compensate. It never mentions 'task_structure', 'stakes', or how they map to compute tier or timeout. The only conceptual hint, 'EVC', does not correspond to any schema parameter, leaving the agent to guess parameter meaning.

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?

States a concrete behavior: 'select compute tier ... and timeout based on EVC,' which is a clear verb+resource distinct from the many sibling cognitive tools. However, the meaning of 'EVC' is unexplained jargon, and 'Fast Path to Deep Deliberation' is evocative but not formally defined.

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?

No guidance on when to use this tool versus alternatives. It implies a compute-budgeting context but never states conditions, exclusions, or sibling trade-offs, which is significant given the large sibling set.

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