Start an autonomous Codex implementation run

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

With no annotations provided, the description carries the full disclosure burden. It proactively states key constraints ('never grants permission to commit, push, deploy...') and behavioral details (isolated worktree, waiting for result, separate chips). It doesn't cover every side effect but provides strong safety context.

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, front-loaded with the core action, then conditionals, then safety. Every sentence adds value with no redundancy or filler.

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 complex orchestration tool with 6 parameters and no output schema, the description covers purpose, safety, and workflow. However, it omits the structure of the 'result' it waits for and any timeout/error behavior, which is a notable gap given no output schema exists.

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% because all six parameters have descriptions in the input schema, so the baseline is 3. The description adds minimal additional parameter semantics, though it aligns 'isolated git worktree' with the useWorktree parameter and implies maxRounds via the turn concept.

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 'Start a saved Codex worker session in an isolated git worktree and wait for its structured result,' which is a specific verb+resource. It also distinguishes from the sibling tool bridge_continue_codex by explicitly naming it as a follow-up, and notes independent calls create separate Codex chips.

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 gives clear conditional guidance: 'If status is waiting_for_fable, the active Claude/Fable coordinator should answer the returned question and immediately call bridge_continue_codex.' It also implies this tool is the entry point. However, it doesn't explicitly state when not to use it or compare with other siblings like bridge_orchestration_status.

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