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

Annotations only declare the mutation/idempotency profile, but the description discloses the concrete behavioral consequences: Codex halts immediately, partial output and file changes are retained, status transitions to interrupted, and the interrupted thread remains resumable via codex_spawn(thread_id=...). It also reinforces idempotentHint explicitly for already-finished tasks.

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?

Every clause earns its place: the core action is front-loaded, followed by state/retention behavior, the no-op case, resumability, and the sibling alternative. No filler despite the density.

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 one-parameter mutation tool with no output schema, the description supplies everything an agent needs: the state transition, side-effect profile, retention semantics, error-case behavior, and where to read results. Nothing material 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?

There is a single parameter with 100% schema description coverage, and the schema already explains it as the 8-digit task id returned by codex_spawn/codex_review. The description adds no syntax or format detail beyond the schema, so the baseline 3 for fully-covered schemas applies.

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 states a specific verb and resource (interrupt a running task) and immediately names the relevant siblings — codex_status for viewing results and codex_steer for redirecting without stopping. An agent can distinguish this from all five sibling tools without opening any 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?

It explicitly covers when to use it (a running task), what happens when the condition does not hold (calling on a finished task is side-effect-free and returns its result), and the alternative when you do not actually want to stop (codex_steer). This is when/when-not/alternative guidance in full.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces that with 固定只读 and adds value beyond them: defect-focused output, severity-sorted results with file:line, async/wait semantics identical to codex_spawn, and a task id return. Timing context (审查通常 1~3 分钟) is also supplied.

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?

Front-loads the core purpose and return shape, then enumerates scopes, then the sibling routing. Dense but every clause carries information; only the repeated scope enumeration overlaps slightly with the enum in the schema.

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 no output schema, the description correctly compensates by describing the return (severity-sorted, file:line issue list) and the async task-id behavior. It is complete enough for an agent to call it correctly without opening the schema.

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 real meaning: the scope→value mapping (分支名 / sha / 自定义说明) and the note that uncommitted needs no value. It does not explain detach's relationship to the async task id, leaving one minor gap.

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 (审查改动 via Codex 内置审查模式), the mode's character (固定只读、以找缺陷为主), and the return shape (按严重度排序、带文件行号的问题列表). It explicitly distinguishes itself from the sibling codex_spawn by intent (改代码 vs 挑毛病).

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?

Gives explicit routing: use codex_spawn to change code, use this only to find faults. It also breaks down when to pick each scope value (uncommitted/base_branch/commit/custom) with the value semantics for each, so the agent can select without inference.

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

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

Annotations declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, and the description corroborates with the critical behavioral warning that by default there is no sandbox and no approval, so Codex will directly modify files and run commands. It also discloses the detach semantics and the thread_id precondition (no still-running task on that thread), which annotations do not convey. It stops short of covering failure modes or rate/concurrency limits.

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 dense paragraph with no filler; the core capability and return value are front-loaded, followed by the sibling routing and then the sandbox warning. It is slightly over-packed with the five sibling name-drops in one breath, but every sentence carries operational information.

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 10-parameter mutating tool with no output schema, the description still explains the return value (8-digit id), how results arrive back to the session, the persistence option, and the default no-sandbox execution posture. Nothing an agent needs in order to call 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 description coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: the detach flag's effect on turn blocking, the wait_s heuristic on which values yield an immediate result, and the constraint that a reused thread_id cannot have a running task. These are genuine additions rather than restatements of the schema text.

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 (dispatch a task to a Codex subagent) and the immediate return value (8-digit task id), plus the wait_s shortcut. It names the sibling tools codex_wait, codex_status, codex_steer and codex_interrupt, so an agent can distinguish this spawn tool from its siblings without opening another 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?

Gives explicit when-to-use guidance: multiple concurrent dispatches are allowed and run in parallel in one resident process; task results auto-return to the session; thread_id is for continuing an old task's context but the thread must have no running task. It also surfaces the alternatives for monitoring/steering rather than leaving them to inference.

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

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

Annotations already declare readOnlyHint and idempotentHint, so safety profile is covered. The description adds valuable behavioral context: immediate return (no waiting), truncation at 6000 characters, full=true to see entire text, and that partial output from interrupted tasks is retrievable. This goes beyond annotations and helps an agent predict output size and completeness.

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 compact and front-loaded with the immediate-return behavior. Sentences are dense but each conveys necessary behavior (listing vs details, truncation, interrupted tasks). Slightly heavy but no wasted words.

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 read-only status tool with no output schema, the description covers the key behavioral aspects: return timing, output structure with/without ids, truncation limit, and partial results from interrupted tasks. It does not explain pagination or exact format of the listing, but given no output schema, the coverage is good enough for correct invocation.

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 both parameters (ids, full) are fully documented in the schema. The description mirrors the schema semantics (e.g., full=true for untruncated) but adds no syntax or format detail beyond what the schema already provides. Baseline 3 applies.

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 this tool reports status of tasks and details, with explicit behavior for with/without ids. However, its difference from siblings like codex_wait or codex_interrupt is only implicit — an agent might confuse status-checking with waiting. It mentions codex_interrupt, but no direct differentiation from the other siblings.

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 says when to omit ids (list all) vs provide ids (detail view). It does not explicitly tell when to use this tool versus codex_wait or codex_interrupt, nor does it exclude cases. Implied usage only.

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

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: the run pivots at the end of the current step, prior work is retained, and calling on a finished task errors. It does not address response format or whether repeated steers compose, keeping it short of a 5.

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?

Front-loaded with the core action and effect, then the precondition and the two sibling alternatives in order of relevance. Every sentence carries distinct information with no 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?

No output schema exists, but the description covers effect, precondition, failure mode, and alternate routes, which is everything needed to invoke this two-parameter steering tool correctly. Annotations carry the safety profile, so nothing material 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%; both parameters are already documented in the schema (id = 8-digit running task id from codex_spawn, prompt = incremental instruction). The description adds only modest framing about writing incremental instructions, so the baseline 3 applies.

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 (append/correct instructions) and resource (a running task), then immediately clarifies the effect: Codex pivots after the current step without restarting and preserves completed work. It distinguishes itself from codex_spawn (continuation) and codex_interrupt (stopping) by name.

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?

Explicitly bounds usage: only valid for running tasks, errors if the task has ended, and in that case directs the agent to codex_spawn(thread_id=...). It also names the alternative for the opposite intent (codex_interrupt). When/when-not/alternatives are all present.

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

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

Beyond the readOnly/idempotent annotations, it discloses non-obvious behavior: timeout returns current state without killing the task, the call can be re-issued to keep waiting, finished tasks return immediately, and progress notifications fire every 10 seconds. This is rich context the annotations cannot convey.

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?

Dense and front-loaded: core behavior first, then timeout/notification behavior, then the alternative-tool pointer. Every sentence carries distinct information with no 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?

There is no output schema, but the description covers what to expect on return (results, current state on timeout, immediate return for finished tasks) plus the rerun and notification behavior. Nothing an agent needs 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. The description adds real meaning on top of the schema by explaining the timeout semantics (returns state, does not kill, re-callable) and the no-ids default, going past raw field documentation.

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 opens with a specific verb and resource: blocking-wait on one or more tasks and returning their results. It also states scope explicitly ('不传 ids 就等本会话全部运行中的任务'), which an agent can use to distinguish it from the other codex_* siblings.

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 gives an explicit alternative and the condition selecting it: '只想看一眼不想等，用 codex_status'. It also clarifies the no-ids default, which effectively tells the agent when this tool is the right choice versus polling status.

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