Anything-vs-Anything Physics

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds real value beyond them by disclosing the return shape: outcome, an intensity 0-10 score, and effects with probabilities. It does not mention auth, limits, or determinism, but for a read-only generative tool the disclosed output structure is the main behavioral gap closed.

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?

Three tight sentences, front-loaded with the core action before the return description and the usage instruction. The illustrative parenthetical is short and earns its place; nothing is redundant.

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 no output schema, the description carries the burden of describing returns and does so (outcome, intensity, probabilistic effects). Optional 'how'/'setting' parameters are schema-documented, so nothing essential is missing; auth/limits remain unaddressed but are minor for a read-only tool.

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 100% with each of the four parameters described, so the baseline of 3 applies. The description's examples ('a rubber duck and a laser') illustrate the flavor of the a/b pairings but add no syntax or formatting guidance beyond the 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 names a specific verb ('resolve') and a clear resource (the outcome of two things meeting) with concrete examples that make the intent unambiguous. It distinguishes itself from rule-based siblings via 'using common sense instead of hand-written rules,' though it never names collision_engine or physics_sandbox explicitly.

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?

Usage is only implied: the 'common sense instead of hand-written rules' phrase hints this is for ad-hoc, fantastical pairings rather than rule-based collision, and 'narrate the result vividly' tells the agent what to do with the output. No explicit when-to-use/when-not or named alternatives are given, and no sibling (e.g., physics_sandbox, collision_engine) is distinguished.

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