Server Quality Checklist

Tool Scores

• quota_resumer_get_snapshotC
  2.9/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the 'local state' context and the refresh behavior, but does not disclose whether the call may block for safetyDelaySeconds or what 'refresh' means in terms of caching or consistency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single concise sentence with no filler or redundancy. It is front-loaded with the action and resource, though it is arguably too minimal to fully inform an agent.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has no output schema and the description does not describe what is returned, what the effect of safetyDelaySeconds is, or when this tool should be preferred over the siblings. For a simple read-style tool this is adequate only in the narrowest sense; an agent would still lack key operational details.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  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 for parameter meaning, but it does not mention safetyDelaySeconds at all. The property name is somewhat self-explanatory and the schema provides type/min/max/default, but the description adds no semantic context beyond that.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a clear action ('refresh') and a specific resource ('local quota and policy state'), going beyond the title. It is distinguishable from the sibling mutation tools (upsert/set) because it implies a read-oriented snapshot operation, though it does not explicitly name a sibling.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives only a vague context ('for the control center') and no guidance on when to use this tool versus open_quota_resume_control_center or the quota_resumer_* mutation tools. There is no explicit when-to-use or when-not-to-use reasoning.

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

• quota_resumer_upsert_policyC
  2.9/5.0
  Behavior3/5

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

  Annotations already convey idempotence, non-read-only status, and non-destructiveness. The description adds one useful behavioral detail: this action does not itself create a Codex scheduled task. However, it does not disclose overwrite/merge semantics or how this policy interacts with policy state.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One tight sentence front-loads the core action and appends only a meaningful clarification about not creating a scheduled task. There is no filler or redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with six required parameters, no output schema, and no per-parameter documentation, the description is under-specified. It behave the meanings of safetyDelaySeconds, continueUntilComplete, and maxCycles unresolved, and provides little contextual guidance for an agent deciding how to construct a valid call.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, and the description provides no explanation for any of the six required parameters. Fields like continueUntilComplete, safetyDelaySeconds, and maxCycles are left to be interpreted purely from their names, which is insufficient for correct invocation.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description gives a specific action — save or update a quota resume policy — and clearly identifies the resource. It also adds a useful clarification that this operation does not create a Codex scheduled task, though it does not explicitly differentiate from sibling policy-state or prewarm tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives no explicit guidance on when to use this tool versus siblings like quota_resumer_set_policy_state or quota_resumer_upsert_prewarm. The only routing hint is the negative statement about not creating a Codex scheduled task; otherwise the intended usage must be inferred from the tool name.

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

• quota_resumer_set_policy_stateB
  3.1/5.0
  Behavior3/5

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

  Annotations already cover idempotency, read-only behavior, and destructiveness, so the safety profile is known. The description adds the sync trigger and target, but does not explain what happens to existing policy state, whether optional fields are ignored in certain states, or what happens on conflicting state transitions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single front-loaded sentence with no repetition or filler. It conveys the key trigger and target efficiently, although it sacrifices behavioral depth for brevity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a mutating tool with five parameters, no output schema, and only minimal annotation context, the description is too thin. An agent cannot confidently determine how optional parameters interact with the required state transition, what the sync does semantically, or when to prefer this over the sibling set_prewarm_state tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must carry the parameter-meaning burden. It implies that the 'state' parameter reflects the policy state being synced, but it gives no meaning for id, nextRunAt, lastMessage, or automationId, leaving an agent without enough context to populate optional fields confidently.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description identifies the action (sync), the resource (policy state in the control center), and the trigger context (after Codex native scheduled tasks are created, paused, completed, or failed). It is clear enough to distinguish the tool from read-only siblings, though it does not explicitly say it overwrites the supplied state value.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It provides a clear trigger condition for when to call the tool, namely after Codex native scheduled task lifecycle events. However, it offers no exclusions or named alternatives, and the sibling quota_resumer_set_prewarm_state creates ambiguity that the description does not resolve.

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

• quota_resumer_upsert_prewarmB
  3.2/5.0
  Behavior3/5

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

  Annotations already indicate a mutating, idempotent, non-destructive operation. The description adds useful context by emphasizing that no Codex scheduled task is created and that the settings are lightweight. It does not contradict the annotations, but it also does not disclose what side effects do occur, such as overwriting existing settings or persistence behavior.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One concise, well-structured sentence that front-loads the core purpose and follows with a valuable scope clarification. Every clause earns its place; there is no filler or repetition of schema/annotation information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 7 parameters, no output schema, and no parameter documentation, the description is too minimal. It does not explain parameter semantics, return behavior, or the relationship to sibling quota_resumer tools. An agent has enough to guess the tool's purpose but not enough to invoke it confidently with correct parameter values.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must carry parameter meaning. It vaguely hints at scheduleMode via 'date or weekly schedule', but it does not explain the meaning or relationship of enabled, weekdays, time, timezone, message, or date. With 7 parameters and 6 required, this is a significant gap.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific action—saving lightweight quota-window prewarm settings for a date or weekly schedule—and clarifies a key boundary: it does not create a Codex scheduled task. This distinguishes it from task-creation workflows, though it does not explicitly compare against sibling tools like quota_resumer_set_prewarm_state.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The intended use is implied by the purpose: use this when saving prewarm settings for a date/weekly schedule. However, it gives no explicit guidance about when to prefer this tool over siblings such as quota_resumer_upsert_policy or quota_resumer_set_prewarm_state, and the only exclusion is that it does not create Codex scheduled tasks.

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

• quota_resumer_set_prewarm_stateB
  3.3/5.0
  Behavior3/5

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

  Annotations already declare idempotentHint=true, readOnlyHint=false, and destructiveHint=false. The description adds that this is a synchronization step following lifecycle events, but it does not describe what 'sync' means in terms of side effects, how state transitions map to parameters, or what happens on failure. This is acceptable but not rich.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, compact sentence with no filler. It front-loads the trigger condition and states the action clearly. Conciseness is excellent, even though other dimensions lack depth.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with five parameters and no output schema, the description is too thin. It omits parameter semantics, the meaning of state values, how nextRunAt/lastMessage/automationIds are used, and what the synchronization outcome looks like. An agent would need additional documentation or inference to call this correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, and the description does not explain any of the five parameters: id, state, nextRunAt, lastMessage, or automationIds. The schema provides types and enums, but the description adds no meaning to any parameter, forcing the agent to guess at semantics.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description identifies a specific action—synchronizing control center state—and a clear trigger context: after a prewarm heartbeat is created, paused, or fails. The prewarm vs policy distinction from sibling tools like quota_resumer_set_policy_state is implied by the resource focus, though the tool name carries much of this differentiation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly states when this tool should be used: after prewarm heartbeat creation, pause, or failure. It does not mention alternative tools or exclusions, but the event-driven context is specific enough to guide selection.

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

• open_quota_resume_control_centerB
  3.4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the tool displays a clickable UI within Codex and requires pre-fetched tasks, which is useful context. However, it does not disclose what happens when elements are clicked, whether the display is modal or transient, or how the passed tasks are rendered—behavioral details that could matter to an agent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences: the first states the tool's function, the second gives the key prerequisite. It is front-loaded, concise, and every sentence contributes useful information. No filler or redundant restating of the tool name.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple and read-only, but the description still leaves an entire parameter ('safetyDelaySeconds') unexplained and gives no detail about the 'tasks' object shape. Since there is no output schema, the description carries the burden of explaining behavior and inputs. It covers the prerequisite but misses enough operational detail that an agent cannot fully reason about how to set 'safetyDelaySeconds' or what the control center will do with the tasks.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  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 for both parameters. It does explain that 'tasks' should contain candidate tasks obtained from Codex's task list, which adds some meaning beyond the schema. However, it does not describe the required fields (id, title), the meaning of 'isCurrent', or the behavior of 'safetyDelaySeconds', which is a meaningful control parameter with default 120 and range 30-3600. This partial compensation is insufficient for a 0%-coverage schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific action ('显示可点击的额度续跑控制中心') and the context ('在 Codex 内'), clearly identifying it as a UI-display tool rather than a data-mutation tool. It is distinguishable from the quota_resumer_* siblings because it is the only one focused on rendering a clickable control center in Codex. It loses one point because the meaning of '额度续跑控制中心' remains jargon-heavy and is not further explained.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives an explicit prerequisite: before calling, use Codex's task list capability to fetch candidate tasks and pass them as 'tasks'. This provides clear when-to-use context. It does not mention alternatives or exclusions, but for a UI-display tool this is a reasonable clear context without needing much negative guidance.

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