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

With no annotations, the description carries the behavioral burden. It discloses the main side effect ('resumes the task') and a key limitation (cannot be used to approve commands or file changes). It does not cover errors or return behavior, but the essential behavioral boundary is clearly stated.

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 a single focused sentence with no filler. It front-loads the primary action and effect, then adds the critical exclusion. 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?

The description identifies the trigger, the effect, and an important non-goal, which is a good foundation. However, with no annotations, no output schema, and 0% parameter coverage, it leaves inputId provenance and answer object structure unexplained. This is a moderate gap for a simple tool, not a fatal one.

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% and the description adds almost no parameter-level meaning. It does not explain what inputId refers to, where it comes from, or how the answers object should be structured. The phrase 'answers to questions' gives a general hint, but it does not compensate for the lack of schema descriptions.

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 ('submit') and resource ('answers to questions returned by codex_pending_input'), and explicitly states it is not for approving commands or file changes. This clearly distinguishes it from sibling tools and leaves no ambiguity about its core purpose.

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 clearly states when to use the tool (when codex_pending_input has returned questions needing answers) and gives a firm exclusion (not for approving commands or file changes). It does not name a specific alternative for approvals, but the when-not is explicit enough for an agent to route correctly.

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?

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose a meaningful trait: cancellation is confirmed only after the terminal state ('终态以后才确认取消'), suggesting asynchronous confirmation. However, it omits other behavioral details such as what happens to the job, whether cancellation is reversible, error cases, or permission requirements.

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 a single front-loaded sentence that states the action and immediately adds the important terminal-state caveat. Every word is purposeful, with no redundant 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 one-parameter tool, the description covers the core action and a key timing nuance, but it omits edge cases such as invalid jobId, already-terminated tasks, or exact return/confirmation semantics. The phrase '终态以后才确认取消' is helpful but somewhat ambiguous about whether the call blocks until terminal state or returns immediately.

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?

The schema has 0% description coverage for the single parameter jobId, and the tool description does not explain it. The parameter's role is inferable from its name and the tool's purpose, but the description adds no explicit meaning beyond 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?

The description states a specific action and resource: '请求中断正在运行的 Codex 任务' (request interruption of a running Codex task). This clearly distinguishes it from siblings like codex_start, codex_status, and codex_steer. The purpose is unambiguous.

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 implies usage when a Codex task is running and needs to be interrupted. However, it does not explicitly state when not to use it, such as for tasks already in a terminal state, nor does it mention any alternative tools or preconditions. Usage context is present but only implicitly.

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?

Discloses a key behavioral trait: the operation is asynchronous and returns a jobId, which is important for agents. Since no annotations exist, the description carries the burden, but it does not explain what compaction means for thread history or how to track the job beyond the jobId.

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 entire purpose, usage context, and async behavior are conveyed in one compact sentence. Every phrase carries information and the core operation is front-loaded.

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 tool, the description is nearly sufficient: it names the input, the purpose, and the return behavior. Missing details such as polling with codex_status or potential side effects are not fatal but would round out the picture for an agent.

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%, but the single parameter threadId is clearly tied to the description's '已有 Codex thread' phrasing. The description adds some meaning by indicating it operates on an existing thread, but it does not explain how to obtain the threadId or its relationship to codex_start output.

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?

Description specifies the verb '压缩' (compact) and the resource '已有 Codex thread 的上下文' (existing Codex thread's context), making the tool's purpose unmistakable. It also adds the scope '适用于长会话', helping distinguish it from sibling Codex tools.

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?

Provides a clear usage context: '适用于长会话' (suitable for long sessions). It does not explicitly mention when not to use it or which alternative to prefer, so it stops short of strong routing guidance.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It only states that the tool 'checks' the listed items, implying read-only diagnostics, but it does not disclose whether the check has side effects, what the output format is, or whether the tool can repair issues. The listed components add some context, but the safety and result behavior remain unclear.

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 compact sentence leads with the verb and enumerates all six check targets with no filler or repeated information. This is appropriately sized for a zero-parameter diagnostic tool.

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?

Given the zero-parameter complexity, the description adequately lists what is checked. However, since there is no output schema, a note on what the agent receives after the check (e.g., a report, list of issues, or pass/fail status) would make it fully self-contained. The description is usable but leaves the result behavior to inference.

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?

The schema defines zero parameters, so there is nothing for the description to explain. The list of checked items effectively serves as the entire parameter surface, making additional parameter semantics unnecessary.

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?

Description uses an explicit verb '检查' (check) and lists the exact resources it inspects: bridge mode, Codex executable, initialization status, sandbox, directory whitelist, and task index configuration. This makes the tool's scope clear and distinguishes it from siblings like codex_status, though it does not explicitly contrast itself with that tool.

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?

No guidance is provided on when to call codex_doctor versus codex_status or other siblings. The listed check areas imply a diagnostic context, but the description never states use cases, prerequisites, or when this tool is not appropriate.

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?

With no annotations, the description carries the burden. It does disclose that the read is realtime and that pagination is supported, which rules out a purely static list. However, it doesn't describe the return shape, cursor source, or any error/rate-limit behavior, so transparency is only partial.

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 short and front-loaded, with the core read action in the first sentence. The pagination note is useful, though the mismatched parameter name costs it a perfect score.

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 simple list tool with no annotations and no output schema, the description should state that it returns a paged list, how cursor is obtained, and how limit controls page size. It covers the paged aspect loosely but omits limit and exact parameter semantics, leaving gaps for a 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 0%, so the description needed to document both parameters. It explains the pagination concept but refers to 'nextCursor' while the actual schema property is 'cursor', and it never mentions the 'limit' parameter or its 1–100 range. This is partial, misleading help.

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 ('read') and a concrete resource ('available model list from the current Codex app-server'). It is clearly distinct from the sibling action tools (start/status/cancel/steer/review/etc.), so an agent can identify it 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?

No guidance is given for when to call this tool versus alternatives. There is no mention of prerequisites such as 'call this before codex_start' or any exclusions, so the agent must infer usage from the name and sibling context.

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?

没有提供任何注解，描述需要承担全部行为披露责任。“列出”暗示只读，但未明确说明该操作不会修改任何任务状态、是否会阻塞等待、对无效 jobId 的表现，以及返回内容的格式。

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?

描述只有一句，核心功能放在开头，没有冗余内容。结构高效，但过短也导致行为与参数信息不足。

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?

对于只有一个参数且是只读列举操作的简单工具，描述给出了输入对象（某个任务）和输出内容（等待回答的 Codex 问题），属于最低可用水平。但没有输出 schema 或注解，也未说明返回问题的具体字段集合，因此仍有明显缺口。

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 参数覆盖率为 0%，而描述没有直接说明 jobId 参数的含义、来源或格式。仅通过“某个任务”间接暗示与 jobId 的对应关系，对唯一参数的语义补偿不足。

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?

描述使用具体动词“列出”和明确资源“某个任务正在等待回答的 Codex 问题”，清楚说明功能。虽然没有像最佳示例那样点名与 codex_answer_input、codex_status 等兄弟工具的区分，但语义本身足以避免直接混淆。

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?

描述隐含使用场景：当需要查看某个任务尚未回答的 Codex 问题时调用。但没有明确说明何时不应使用，也没有提及应改用 codex_answer_input 或 codex_status 的条件。

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action (start native code review) and the constraint (only explicit targets), but doesn't disclose what happens to the thread, whether it's a long-running operation, whether it modifies state, or what the delivery modes (inline/detached) mean behaviorally. For a tool that likely mutates or drives a thread, this is a significant gap.

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 very short (one sentence) and front-loads the core action. It's efficient, but the brevity comes at the cost of missing critical parameter semantics and behavioral context. Still, every word earns its place, and the constraint is clearly stated.

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?

Given the tool has 3 parameters, a nested target object with 4 enum subtypes, no output schema, and no annotations, the description is far from complete. An agent would need to understand what 'delivery' means, what each target type implies, and what the review process entails. The description only covers the 'explicit target' requirement, leaving major gaps 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 description coverage is 0%, so the description must compensate. The description mentions '明确的审查目标' (explicit review target), which maps to the 'target' parameter, but doesn't explain the meaning of 'threadId', 'delivery', or the target subtypes (uncommittedChanges, baseBranch, commit, custom). The nested object structure with 4 subtypes is completely undocumented in the description, leaving the agent to guess at semantics.

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 ('启动原生代码审查' - start native code review) and resource ('已有 Codex thread' - existing Codex thread), distinguishing it from sibling tools like codex_start and codex_status. It also adds a constraint ('仅接受明确的审查目标' - only accepts explicit review targets), which helps clarify scope. However, it doesn't explicitly name sibling tools for differentiation, so it loses a point.

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 implies usage context: it operates on an existing thread and requires an explicit target. The constraint '仅接受明确的审查目标' gives some guidance on when to use it (when a clear review target exists). However, it doesn't explicitly state when NOT to use it or mention alternatives like codex_steer or codex_status for other operations on threads.

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?

The description discloses that the sandbox is read-only and that permissions are determined by user startup configuration, not tool parameters. However, with no annotations provided, the description carries the burden; it doesn't mention what happens to the job after starting, how to check status, or any side effects beyond returning a jobId.

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 concise and front-loaded with the main action and return value. It includes important behavioral notes about read-only sandbox and permissions. Slightly dense but each sentence adds value.

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 tool that starts a task, the description covers the core action, return value, model selection, and sandbox constraints. However, it lacks details about how to use the returned jobId, how to handle errors, or what happens if the thread doesn't exist. Given the sibling tools for status/cancel, an agent might need more guidance on the lifecycle.

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. It mentions prompt, cwd, model, and threadId implicitly (new or existing thread), but doesn't explain the format or constraints of each parameter beyond what the schema already shows. It adds some context about model selection but not enough to fully compensate for the 0% coverage.

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 the tool starts a task in a new or existing Codex thread and immediately returns a jobId. It also mentions the model parameter for specifying the task model, which distinguishes it from sibling tools like codex_status or codex_cancel.

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 explains that it can be used in new or existing threads and that the model parameter can specify the model. It doesn't explicitly say when to use alternatives, but the context of starting a task is clear enough to differentiate from status/cancel/steer tools.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond the schema by explaining that passing cursor returns only new output since the last query, and that waitMs enables long polling up to 30 seconds. This provides meaningful behavioral context about incremental retrieval and polling behavior. It does not explicitly state side effects, but the '查询' wording implies read-only intent, and for a status tool this is reasonably transparent.

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 two short sentences. The first sentence front-loads the primary purpose, and the second succinctly explains the two optional parameters' behavior. There is no redundant or filler content, making it easy to parse and act on.

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, the description provides enough to invoke the tool correctly (jobId, cursor, waitMs) but does not explain the return value structure, possible statuses, or how to detect completion. Given the complexity of a status/reply tool and the absence of output schema, this is a notable gap. The description could be more complete by indicating what the response contains or how to interpret statuses, but it is minimally viable.

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. It does so for cursor and waitMs by explaining their semantics (incremental output and long polling duration), which are not apparent from the schema alone. jobId is not described explicitly, but its role is self-evident as the task identifier. The description adds significant meaning for two of the three parameters, making the tool more usable.

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 the tool's purpose: '查询 Codex 任务状态和已经收到的助手答复' (query Codex task status and already received assistant replies). This is a specific verb (query) and resource (task status + replies), and it distinguishes itself from sibling tools like codex_start, codex_cancel, and codex_pending_input by focusing on status retrieval. The additional details about cursor and waitMs further clarify its role as a polling mechanism.

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 implies usage (querying status and replies, especially with incremental updates or long polling), but it does not explicitly state when to use this tool versus alternatives like codex_pending_input or codex_review. There are no exclusions or explicit recommendations, leaving the agent to infer the appropriate context from the tool name and description.

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?

No annotations are provided, so the description carries the full responsibility for behavioral disclosure. It does add one useful guarantee: it will not change sandbox or approval policy. However, it does not disclose whether the prompt is appended or replaces existing instructions, whether multiple calls are allowed, or what effect it has on already-generated content.

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 a single sentence that front-loads the core action and scope, then adds a valuable non-effect. There is no filler, redundancy, or unnecessary detail.

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?

Given no output schema, no annotations, and zero schema description coverage, the description is too sparse. It explains the general purpose and one non-effect, but it omits explicit parameter mapping, when-to-use guidance, and behavioral side effects. An agent can guess, but it is not fully equipped to call this tool correctly without further documentation.

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 0% and the description does not explicitly explain the parameters. It hints that prompt is the instruction and jobId refers to the running turn, but it never names them or describes expected formats or behaviors. The parameter names are self-explanatory, yet the description adds no explicit value beyond the JSON 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?

The description uses a specific verb and resource: '补充指令' (supplement instructions) to the '当前运行中的普通 Codex turn' (currently running normal Codex turn). It also distinguishes itself from siblings by scoping to normal running turns and explicitly noting it does not change sandbox/approval policy. An agent can separate this from codex_start, codex_cancel, codex_review, and the input-related tools.

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 implies the use case: add instructions to an already running Codex turn. However, it does not explicitly state when not to use it or name alternatives, such as codex_pending_input or codex_answer_input for turns awaiting input. The routing is left to inference, not explicit guidance.

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