rush_hallu_guard

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

No annotations are provided, so the description carries the full disclosure burden. It only states that the tool 'audits' imports; it doesn't say whether the audit is read-only, how 'installed packages' is determined (current environment, requirements file, or lockfile), or what happens when problematic imports are found (report, exit code, or autofix).

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 9-word single sentence is front-loaded with the verb and contains zero filler; every word earns its place. The brevity that hurts other dimensions is an underspecification problem, not a structure problem.

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?

An output schema exists, so return values need no explanation, but invocation context is thin: path semantics, read-only vs. modifying behavior, and how 'installed packages' is resolved are all implicit. For a guard-style tool, an agent needs to know whether invoking it can modify the repo or fail the build before committing to it.

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% - the 'path' property has no description - and the tool description never mentions the parameter. An agent must guess whether path points to a file, directory, or project root, and what the default '' resolves to; the description adds nothing beyond what the param name already implies.

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 ('audit'), resource ('code imports'), and comparison baseline ('installed packages and stdlib'), so the core function is immediately clear. It also distinguishes itself from likely-overlapping siblings like rush_dead, rush_typecheck, and rush_arch_guard by narrowing to import resolution, though it stops short of explicitly naming an alternative.

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 is given on when to use this tool vs. rush_dead, rush_arch_guard, or rush_typecheck. There are no exclusion conditions, no mentioned alternatives, and no context signals such as 'run after dependency changes' - selection is left entirely to the agent's inference from the tool name.

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