antigravity_gui_followup

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

With no annotations, the description must carry the burden, and it does disclose non-obvious behavior: the tool rejects calls against busy chats, after model changes, and with unsent drafts, and the optional thread id enables watching the new round. It still omits whether the correction mutates or appends to prior state and what error feedback looks like, but the refusal semantics are genuinely useful.

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?

Three tight sentences with the core action and prerequisite front-loaded and zero filler. The refusal clause is compressed to near-telegraphic form ('unsent drafts'), which trades a little precision for brevity.

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?

An output schema exists, so return values need not be explained, but for a 4-parameter tool with 0% schema coverage and no annotations the description is thin: it never says what the correction does to prior task context or clarifies workspace_path vs. task_id. Adequate to call correctly, incomplete to call confidently.

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 0% across 4 parameters, so the description has to compensate. It explains notify_codex_thread_id's purpose ('watch the new round') and ties task_id/workspace_path to 'the same completed GUI task', but prompt is undocumented (append vs. replace semantics unknown) and workspace_path's relationship to task_id is never clarified.

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+resource: sending corrections to an already-completed GUI task, keyed by task_id. It implicitly distinguishes itself from antigravity_gui_start_task (new tasks) but never names a sibling, so the differentiation must be inferred from 'same completed GUI task'.

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 phrase 'the same completed GUI task' establishes the prerequisite that a prior completed task exists, and the refusal list ('busy chats, model changes, unsent drafts') gives concrete when-not-to-use conditions. It stops short of naming an alternative tool to use when those refusals apply.

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