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

With no annotations, the description must carry the full behavioral burden. It does disclose one genuinely important non-obvious behavior: dangerous direct-delete commands are auto-intercepted and converted to decline. It does not say that the call blocks/wait (waitMs up to 45s), whether decisions are final, or what happens on a timeout, leaving meaningful gaps for a mutation-style approval tool.

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?

Two sentences, no filler, and the scope of the tool is front-loaded ahead of the auto-intercept caveat. Could be tighter only in that the parenthetical category list is somewhat enumerative.

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?

Badly overstated; rescored to 3. For a 6-parameter tool with a nested answers object, a blocking wait parameter, and no output schema, an agent still lacks guidance on decision choice (accept vs decline vs cancel), timeout behavior, and whether a returned result must be re-polled via codex_poll. Those omissions matter 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 100%, so baseline is 3. The description's mention of 用户交互提问 hints that answers are required only for user_input cases, which adds a small amount beyond the schema, but it says nothing about decision semantics (when to choose cancel vs decline) or the waitMs trade-off.

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 (回复/approve) against a specific resource (Codex 反向审批请求) and enumerates the request categories it covers: command execution, file changes, permission requests, and user-input questions. Siblings (codex_poll, codex_send, codex_cancel, codex_sessions) are not named, but their verbs are distinct enough that confusion is unlikely.

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?

Implies usage — respond when Codex has a pending reverse-approval request — but never states when not to use it, nor that interactionId must first be obtained from a snapshot/pendinApproval (that hint lives only in the schema) or that codex_poll is the way to discover pending requests. No explicit alternative routing.

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, and it does add real behavior: it sends an interrupt, waits up to 5 seconds for confirmation, and keeps the system busy until the old command confirms it stopped to avoid concurrent write conflicts. It omits what happens if the 5-second wait expires or how failure is reported.

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 compact sentences with the core action front-loaded, followed by the wait behavior and the concurrency rationale. No sentence is redundant.

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 two-parameter mutation with no output schema and no annotations, the description covers the action, its timeout, and its concurrency side effect well. It could be more complete by describing the outcome when cancellation times out or the target turn is not running.

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 threadId and turnId are already documented as the session ID and turn ID. The description adds no further meaning about which turn to cancel or how the IDs relate to the running turn, 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?

The description names a specific verb and resource: cancel the currently running Codex execution turn, and it is clearly distinct from siblings like codex_send or codex_poll. It does not explicitly contrast itself with those siblings, which keeps it from a 5.

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?

Usage is only implied: you cancel a running turn. There is no explicit statement of when to prefer this over alternatives, no prerequisite conditions, and no note on what to do if there is no running turn.

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 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.

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the initial wait window (default 10s) and that incomplete work returns a snapshot plus recommended backoff for the next poll, but it omits side-effect and safety details such as session creation, permission implications, or what actions Codex may take.

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 front-loaded sentences with no wasted text. It moves from purpose to configurable behavior to the asynchronous wait/return behavior in a logical order.

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 nine parameters and no output schema, the description covers the core call pattern and the important partial-result behavior. The main gap is sibling routing: it does not explain how to continue with codex_poll after receiving a snapshot or when approval/cancellation tools are relevant.

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 every parameter is already documented structurally. The description only notes workspace directory, model, and permission mode, adding little meaning beyond the schema and leaving prompt, threadId, waitMs, effort, serviceTier, and safeTrashOnly 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?

The description states a clear verb and resource: send a prompt to Codex, either creating a new session or continuing an existing threadId. It also distinguishes the initial wait behavior from later polling, but it does not explicitly name or contrast sibling tools such as codex_poll 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?

Usage is implied: use this tool to send prompts and optionally continue an existing threadId, with a partial-result path for polling. However, the description does not explicitly state when to use it instead of codex_poll, codex_approve, or codex_cancel, nor does it describe exclusions or prerequisites.

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; '查看本地' does convey read-only local access, which is the key behavioral fact. However, it says nothing about pagination/limit behavior, ordering, performance on large histories, or whether any auth/config is needed.

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?

Two compact sentences, front-loaded with the list/detail distinction and followed by the source-coverage scope note. No filler, though the source list is somewhat peripheral to how the tool is invoked.

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 zero-required-parameter read tool with a fully described schema, the definition is adequate to call it correctly. Since there is no output schema, the description could have said more about what the list/detail results look like, but the schema's threadId text partially compensates.

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 cwd, limit and threadId are already fully documented with defaults and bounds; baseline is 3. The description adds only the cross-cutting '全来源 (CLI / VS Code / 桌面端 / exec / appServer)' context, not parameter-level meaning.

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 (查看) and resource (本地 Codex 原生历史会话列表 / 指定会话详情), and covers both list and detail modes plus source coverage. Siblings (codex_poll/send/approve/cancel) are action-oriented, so the read-only history tool is easy to tell apart, though the description never names a sibling explicitly.

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 two operating modes are implied — omit threadId to list, supply it to read a session — and the schema's threadId description confirms this. There is no explicit when-to-use / when-not-to-use guidance or mention of alternatives, so usage must be inferred.

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