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

With no annotations, the description carries the behavioral burden. It does disclose the key stateful behavior: this tool continues an existing conversation and preserves previous context. However, it does not mention side effects, whether the conversation is modified, error cases, auth requirements, or rate limits.

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 two sentences long, front-loads the core purpose, and every sentence adds value. It names the resource, the key parameter source, and representative use cases without 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 simple conversational tool, the description covers purpose and usage context and the schema covers all parameters. However, with no output schema, it does not state what the tool returns, which would help an agent understand the result of continuing a conversation. Edge cases are also unaddressed.

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 parameter meanings are already fully documented. The description reinforces that conversation_id comes from agy_prompt, but this is also stated in the schema. It adds no extra semantics for prompt or timeout_seconds.

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 opens with a specific verb and resource: '延续一个已有的 Antigravity 对话' (continue an existing Antigravity conversation). It clarifies that this tool is for continuing prior context using the conversation_id from agy_prompt, which distinguishes it from the sibling agy_prompt.

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?

It explicitly states suitable scenarios: multi-turn interactions such as iterative code modification and follow-up questions. It references agy_prompt as the source of conversation_id, implying agy_prompt is for starting conversations, but it does not explicitly say 'use agy_prompt for new conversations' or list exclusions.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It conveys a read-only query action ('查询'), which is useful, but it does not mention response format, pagination, ordering, rate limits, or authorization needs. This is minimally transparent but not richly detailed.

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 tool's action and target resource. There is no filler, and the essential information is front-loaded.

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 low complexity (no parameters, no output schema) and clear purpose, the description is largely sufficient for an agent to invoke the tool correctly. The only minor gap is the absence of any detail about the returned list contents or behavioral guarantees, but this is not critical for a simple model-list query.

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 is empty (0 parameters), and the baseline for zero-parameter tools is 4. The description adds no parameter-specific detail because none is needed; there is nothing beyond the schema for the agent to disambiguate.

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 uses a specific verb ('查询') and resource ('Antigravity 可用的 AI 模型列表'), clearly stating that the tool lists available AI models. This distinguishes it from the sibling tools agy_prompt and agy_conversation, which appear to handle prompt and conversation tasks rather than model listing.

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 usage: call this tool when you need to see available AI models on Antigravity. However, it does not explicitly state when not to use it, nor does it mention any alternative tool or edge cases, so the guidance remains implicit rather than explicit.

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 provided, the description carries the full burden of behavioral disclosure. It explicitly warns that Antigravity can read and write files, run commands, and search codebases, which are significant behavioral traits. It also discloses the return of a conversation_id, but does not mention potential side effects, permissions, or rate limits.

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 three sentences with no fluff: purpose, tool capabilities, and return/coordination hint. Each sentence adds distinct value and the most important information is front-loaded in the first sentence.

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 7 parameters and no output schema, the description provides the essential context: what the tool does, what the assistant is capable of, and that responses include conversation_id for follow-up. It does not detail the full response structure or edge cases, but the 100% parameter schema coverage compensates for most remaining gaps.

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 coverage is 100%, so the input schema already documents all 7 parameters, including defaults and enum values. The description adds no additional parameter-level meaning beyond the schema, so the 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 uses a specific verb and resource: '发送提示词并获取响应' from Antigravity AI, and clearly names its function as a coding-task assistant. It also distinguishes itself from the agy_conversation sibling by explaining that this tool returns a conversation_id for multi-turn use with that 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 clear usage context by stating it is suitable for code generation, review, refactoring, and debugging tasks. It also signals when to involve agy_conversation for multi-turn dialogue, though it does not explicitly say when not to use this tool or describe cases where agy_models would be more appropriate.

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