codex_gravity_watch_completion

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

With no annotations, the description carries the full burden and does add real signal: it blocks while Codex is busy, will not silently retry uncertain delivery, and grants exactly one follow-up per round. But it leaves key behavior unexplained — whether the watch persists after the call returns, what occurs at timeout_seconds, and whether re-invocation is idempotent or duplicates a watch.

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 primary action front-loaded and no filler. The density is high but each sentence conveys distinct information; only the 'detached completion watch' phrasing asks extra parsing work of the reader.

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 described, and the blocking/no-retry semantics are covered. Still, for a six-parameter, unannotated, state-mutating tool the description omits polling/timeout behavior and lifecycle details, leaving the agent under-informed before invoking it.

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 six parameters, so the description must compensate and largely does not. It only indirectly maps to task_id and codex_thread_id; resume, poll_seconds, timeout_seconds, and workspace_path receive no meaning at all, leaving half the surface undocumented in both places.

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 gives a specific verb pair ('Register/resume') and resource ('a detached completion watch'), scoped to an owned Antigravity task and an existing Codex thread UUID. It implicitly distinguishes itself from the status/cancel siblings by framing the action as registration/resumption, though it never names them and the term 'detached completion watch' is jargon an agent must infer.

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 implies prerequisites ('owned Antigravity task', 'exact existing Codex thread UUID') and signals the authorization role ('Explicitly authorizes one completion follow-up for this round'). However, it never states when to use this versus codex_gravity_completion_status or codex_gravity_cancel_completion, nor what happens if a watch already exists without resume=true.

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