list_available_models

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

With no annotations, the description carries the full behavioral burden. It usefully signals that results are session-scoped and dynamic ('live', 'currently available'), but says nothing about what the listing returns (names vs. full metadata), whether it is cached, or any failure mode when no session is connected. Adequate but incomplete for a tool with zero annotation coverage and no output schema.

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?

Two sentences, zero waste, with the resource and scope front-loaded and the usage condition following. Every clause earns its place.

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 zero-parameter list tool, purpose and the routing rule to dispatch_gemini_agent are covered. The only gap is the return shape, which matters slightly more here because no output schema exists to describe 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?

The tool takes no parameters, so there is nothing for the description to disambiguate and the schema is trivially complete. Baseline 4 applies for a zero-parameter tool.

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 (List) and resource (live models available from the connected Antigravity IDE session), and scopes it to the current session rather than a static catalogue. It also names the downstream consumer, dispatch_gemini_agent, so an agent can place it among its siblings.

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?

Gives an explicit call condition: invoke before dispatch_gemini_agent when the exact, currently-live model name is unknown. That is a concrete when-to-use trigger tied to a named sibling, leaving little to inference.

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