codex_poll

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

With no annotations, the description carries the full burden and does well: it discloses the truncated exponential backoff cadence (20s -> 40s) and the early-return triggers, which are non-obvious runtime behaviors. It stops short of stating that it is a read-only, non-mutating operation or anything about payload size, but the key timing semantics are covered.

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 short sentences, front-loaded with the purpose followed by the waiting strategy and return conditions. No filler or repetition of the parameter list.

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 polling tool with no output schema, it conveys the essential contract: it returns a snapshot plus events, and it terminates on completion/approval/disconnect. A brief note on how the cursor advances or what the snapshot contains would close the remaining gap, but nothing needed to invoke it correctly 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 coverage is 100%, so the baseline is 3, but the description adds value by explaining what omitting waitMs does (automatic backoff), which links the parameter to observable behavior rather than just its 0..45000 range. cursor and threadId/turnId semantics are left to the schema.

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 and resource ('轮询当前运行中的 Codex 任务进度') and scopes it to running tasks, which cleanly separates it from the sibling write/control tools (codex_send, codex_approve, codex_cancel). An agent can identify the operation without opening the schema.

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?

Explains the default waiting mode when waitMs is omitted and enumerates the three conditions under which it returns early (completion, approval trigger, disconnect). It gives clear usage context but does not explicitly contrast with alternatives such as codex_sessions for discovering threadIds.

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