Granular Screen

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

Annotations declare readOnlyHint=true and openWorldHint=false, but the description goes further by disclosing that each result includes fidelity='correlation' and an honest [low, high] band, that the band IS the oracle, and that these are not exact solutions. It also clarifies the idealized monodisperse scope and the lack of an external solver.

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?

Despite being long, the description is tightly packed: it front-loads the core nature ('Closed-form granular/powder-mechanics oracles'), then uses a clear dispatch structure for each mode. Every sentence contributes either semantics, units, formulas, or escalation guidance, so the length is justified by the tool's complexity.

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?

With 17 parameters, no output schema, and minimal annotations, this description provides a remarkably complete picture: modes, formulas, parameter requirements, bands, units, and escalation path. It even states the return convention (fidelity and a low/high band), making the tool callable with little ambiguity.

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 0%, so the description carries the full burden, and it succeeds. It maps each `problem` dispatch to the relevant parameters, gives formulas, units, and example values (e.g., RCP ≈ 0.637, FCC/HCP 0.7405), and explains what each mode computes. This is essential value beyond the bare schema.

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 states a specific purpose: closed-form granular/powder-mechanics correlations with banded uncertainty estimates. It clearly distinguishes itself from the DEM/YADE solvers by naming the analytic twin nature and listing exact dispatch modes ('packing', 'beverloo', 'beverloo_exponent', 'repose', 'repose_monotone').

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?

It explicitly tells the agent when to use this tool versus alternatives: 'Escalate to dem_pack_submit / dem_flow_submit (the real YADE solve) for polydisperse mixes, non-spherical grains, cohesion, or geometry this monodisperse idealization can't see.' It also explains that this is a screening/correlation tool, not exact theory.

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