compact

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It reveals key behaviors: older turns are summarized, recent turns kept verbatim, and content is replayed into a fresh Gemini Live session. However, it doesn't disclose side effects—like whether the original session is destroyed, whether there's a lossy summary tradeoff, identity/auth implications, or rate limits. The core behavior is described but deeper consequences are not.

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 compact and front-loaded. The first sentence states the purpose immediately. The subsequent sentences add behavioral detail and usage guidance in just a few lines with zero wasted words. Every sentence 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?

Given this is a zero-parameter tool with an output schema, the description covers the key behavioral aspects: what happens to old turns, what happens to recent turns, and how context is preserved. The only gap is return-value semantics that the output schema presumably covers. For a tool of this complexity, the description is largely complete. A clear 'when not to use' or reference to the output schema would nudge it to 5.

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?

With 0 parameters and a 100% schema description coverage, the parameter baseline is 4. There are no parameters to document, which is itself a meaningful signal the tool takes no input. The description appropriately focuses on the tool's behavior rather than parameters, making this dimension inherently satisfied.

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 verb+resource: 'Compact conversation history and reconnect.' It explains the behavior (summarizes older turns, keeps recent verbatim, replays into a fresh session). It also distinguishes from new_vision by noting context preservation. However, it doesn't explicitly differentiate from the other sibling compact-like tools, though its unique verb/behavior is clear.

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 explicitly says 'Use instead of new_vision when you want to preserve context,' which directly addresses when to use this tool versus an alternative. It states clear context (when context preservation matters) but doesn't cover exclusions or when NOT to use it. Still, naming the specific alternative is strong guidance.

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