continue_run

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

Annotations already signal readOnlyHint=false and destructiveHint=false. The description adds useful context: the run is asynchronous and can run in the same workspace or an isolated worktree. It does not explain side effects, return behavior, or what happens to the original conversation, but the annotations lower the burden.

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?

A single well-structured sentence with no filler. The key qualifiers — completed, new asynchronous run, same workspace or isolated worktree — are front-loaded and every word 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?

With 7 parameters and no output schema, the description is too thin. It does not explain how results are retrieved, what the asynchronous execution entails in practice, how workspace/worktree isolation is selected, or the effects of optional parameters. The schema provides enums and bounds, but substantial operational context is missing.

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%, so the description must compensate, but it never mentions run_id, prompt, model, effort, max_retries, model_policy, or timeout_minutes. Only from the tool name and phrase 'completed... conversation' can run_id and prompt be inferred; all optional parameters remain unexplained.

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 ('Continue') and a clear resource ('completed Antigravity conversation'), and specifies the result is 'a new asynchronous run'. This distinguishes it from siblings like start_* and resume_team, though it does not explicitly name alternatives.

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 context is clear: use it when a conversation is completed and should be continued as a new run. However, it does not state when not to use it or directly compare against alternatives such as resume_team, cancel_run, or start_analysis.

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