Unity AI Bridge

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

With no annotations provided, the description carries the full burden and does so effectively. It discloses critical behavioral traits: the tool modifies manifest.json, triggers package resolution and domain reloads, has completion delays, and specifies operational constraints (what cannot be removed).

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 efficiently structured with zero wasted sentences. It front-loads the core action, then provides essential notes and usage guidance in a logical flow, all in four concise sentences.

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 destructive tool with no annotations and no output schema, the description is quite complete—covering purpose, constraints, side effects, and prerequisites. The main gap is lack of explicit return value information, but it hints at results being sent after reload.

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 only 50% (packageId has description, requestId does not). The description doesn't explicitly discuss parameters, but it implies the packageId usage through context. It compensates somewhat by mentioning package listing first, though it doesn't fully address the undocumented requestId parameter.

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 states the specific action ('remove/uninstall'), the target resource ('a package from the Unity project'), and distinguishes it from sibling tools like 'package-add' and 'package-list' by specifying its destructive removal function.

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 provides clear context on when to use this tool (after listing packages with 'package-list') and mentions constraints (built-in packages and dependencies cannot be removed). However, it doesn't explicitly state when NOT to use it or compare it to all alternatives like 'assets-delete' for asset removal.

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