rules_evaluate

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

No annotations are supplied, so the description carries the full behavioral burden. It does well to declare 'Nothing is written' and to name the return payload (verdict, deciding rule line, evaluated expressions), but it never says what happens on a compile error, whether an emulator must be running, or how draft evaluation differs in cost or side effects.

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 that opens with the purpose and closes with the safety clause and return shape. It is dense with semicolons but every clause carries information; minor cost is that enumerating all five methods makes it slightly harder to scan.

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 17-parameter tool with no output schema and no annotations, the description covers the essential gaps: what is simulated, that nothing is persisted, and what comes back. Remaining omissions are error behavior and any prerequisite about the emulator being active.

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 100% across all 17 parameters, so the schema already documents uid, source, existing, object and the rest. The description only gestures at the uid/claims/idToken axis ('as a given user or unauthenticated') and the source/draft axis; it adds little beyond what the schema states.

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 specific verb and resource: evaluate rules in force or a draft against a hypothetical request, enumerating the five methods and the Firestore/Storage targets. That framing separates it cleanly from siblings like rules_get (fetch source) and rules_list_denials (post-hoc denials).

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 conditional 'whether a request would be allowed' plus 'in force (or a draft)' makes the use case clear, and 'Nothing is written' signals it is a dry-run rather than an actual operation. It stops short of naming alternatives, e.g. pointing at rules_get when the goal is to read the rules text rather than evaluate them.

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