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

With no annotations provided, the description carries the burden of revealing behavioral traits. It discloses what is returned (model text, interaction_id, model, usage metadata, status), a safety guarantee ('Never returns credentials'), and the conditional behavior of store=true generating a conversation_id. While it does not mention rate limits or side effects, it covers the most critical behavior for an AI agent selecting this tool.

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 four sentences, approximately 70 words, with each sentence contributing unique information: purpose, default model, store mechanism, return values and safety. It is front-loaded and contains no redundant filler, making it highly efficient.

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 the tool complexity (7 params, no annotations, no output schema), the description is reasonably complete. It explains the tool's operation, return fields, and conversation continuation. It does not cover error scenarios or detailed response formatting, but the schema covers parameter specifics, and the description lists the key output components.

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 100%, so the baseline is 3. The description adds value by explaining the relationship between store and previous_interaction_id, and by stating the default model, which complements the schema. It does not describe every parameter but enriches the context for the conversation flow.

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: 'Send a prompt to the local Antigravity CLI and return the model text output.' This is specific with a verb and resource. However, it does not explicitly differentiate from the sibling tool 'gemini_models', missing the chance to contrast with a likely model-listing tool.

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 useful context about the default model, store=true for conversation continuation, and return values. However, it offers no explicit guidance on when to use this tool versus alternatives (e.g., gemini_models) or any when-not scenarios. The usage is implied but not explicitly framed as a choice.

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

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

With no annotations, the description discloses that the tool is local to the Antigravity CLI and returns filtered model ids and display names. However, it does not explicitly mention side effects, permissions, or failure modes, though for a simple list operation these may be less critical.

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 a single sentence that immediately states the purpose and separates the return value. It is concise, front-loaded, and contains no filler, earning the highest score.

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 simple list tool with one optional parameter and no output schema, the description provides sufficient context: it states the local scope, the list action, and the return fields. It is complete for the tool's simplicity, though it could benefit from explicit sibling differentiation.

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 full coverage (100%) of the 'filter' parameter, describing it as a case-insensitive substring. The description adds minimal extra meaning by mentioning 'filtered' output, but it does not explain parameter syntax or behavior beyond the schema.

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 lists models available to the local Antigravity CLI, using a specific action ('List') and resource ('models'). It also mentions the return format (filtered model ids and display names), which distinguishes it from the sibling 'gemini' tool that likely performs a different action.

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 implies the tool is used to discover available models, but it does not explicitly state when to use it versus the sibling 'gemini' tool. No alternative or when-not-to-use guidance is provided, leaving room for confusion in tool selection.

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