orch_criterion

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

Without annotations, the description carries the burden of behavioral disclosure. It does reveal that the mass-displacement scale is exposed as a free parameter and that a sensitivity sweep is performed, which is helpful. However, it does not mention whether the tool is read-only, any side effects, or the return format (no output schema exists), leaving some ambiguity.

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 sentence that packs in the formula, the free parameter, and the sweep behavior without any filler. Every phrase contributes to understanding.

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 specialized scientific computation with three parameters and no output schema, the description provides the core formula and main behavior, but it does not specify the output structure, error conditions, or how the sweep results are presented. Given the complexity and lack of output schema, a bit more detail would make it more self-contained.

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 already covers all three parameters with descriptions, but the description adds meaningful context by naming the mass-displacement scale (separationM) as the free parameter and indicating the tool sweeps across orders of magnitude. This supplements the schema by clarifying the intended use of the parameters.

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 identifies the tool as computing Penrose's objective-reduction criterion τ = ℏ/E_G, with the mass-displacement scale exposed as a free parameter and a sensitivity sweep. It uses a formula rather than an explicit verb, which is slightly less direct, but the scope is well-defined and distinguishes it from related sibling tools like orch_decoherence.

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 that this tool is for sensitivity analysis via the sweep across four orders of magnitude, but it does not explicitly state when to prefer this over sibling tools or exclude alternatives. No direct comparison to orch_decoherence or other tools is provided.

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