gemini_chat_continue

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals important behavioral traits: model inheritance from conversation start, rejection of model changes with the specific error code 1050 (ModelInvalid), and the workaround via gemini_chat_new. This goes beyond what the tool's name implies and helps the agent avoid predictable errors.

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 concise and well-structured, with the primary purpose stated upfront in a single sentence. The second sentence adds critical technical context about model inheritance and error handling, each part earning its place. No unnecessary words or redundancy.

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 two-parameter tool with an output schema, the description is fairly complete. It covers the main operation, a key error scenario, and provides an alternative tool usage. However, it does not mention what happens if the label does not exist or if the conversation context is invalid, which could be relevant for error handling. Overall, it is sufficient but not exhaustive.

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 input schema already provides descriptions for both parameters (label as existing session label, prompt as continuation text) with 100% coverage. The description adds minimal new semantic information about the parameters, primarily restating the purpose of 'prompt' and 'label' in the context of continuing a conversation. Thus, a baseline score of 3 is appropriate.

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 tool's function: sending a prompt to an existing conversation and returning a response. It specifies the resource (existing conversation) and action (send prompt), and distinguishes itself from siblings by explicitly mentioning that creating a new label with gemini_chat_new is the alternative for different models.

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 explicit usage guidance, stating that the model is carried over from the conversation start and that mid-conversation model changes are rejected. It further recommends using gemini_chat_new to start a new label if a different model is desired, clearly defining when to use the alternative.

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