Codex Reset

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

Annotations already mark it read-only and closed-world, and the description adds that data is sourced from codex-reset.com rather than an official API and reflects current state. This third-party tracking detail is useful context for interpreting results; no contradiction with annotations.

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 sentence front-loads the resource and purpose, and every clause earns its place. It is neither padded nor under-specified at the macro level.

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 read-only status tool with one optional, fully documented parameter, the description covers source and intended use. It does not describe the exact status values or response shape, but no output schema exists and an agent can call the tool correctly from the provided information.

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 only parameter, locale, is fully documented in the schema with its enum and default, so the description does not need to repeat it. Because schema coverage is 100%, baseline 3 is appropriate.

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 specifies the resource ('OpenAI Codex service state') and adds the purpose of distinguishing outage from usage limit, so an agent knows what this tool reports. It does not explicitly contrast with sibling tools get_reset_forecast/get_reset_timeline, but the stated purpose makes the resource clear.

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 phrase 'to tell an outage apart from a usage limit' provides a concrete when-to-use context without needing to open the schema. It does not name sibling alternatives or give a when-not-to-use rule, but the intended scenario is clear enough.

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 annotations already declare readOnlyHint=true and openWorldHint=false. The description adds useful behavioral context beyond that: 'A forecast, not a promise' signals uncertainty, and it lists the result contents (probability, confidence, last confirmed reset time, active official signal).

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 with no filler. The core value is front-loaded, and the 'forecast, not a promise' disclaimer is concise rather than repetitive.

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 with one optional parametereb and no output schema, the description covers the key output components and the uncertainty framing. It could be more explicit about the probability format or range, but an agent can invoke the tool correctly without needing more.

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 only parameter, locale, is fully documented in the schema with an enum and a default value. The description adds nothing about locale semantics, but with 100% schema description coverage, the baseline score of 3 is appropriate.

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 identifies the resource (OpenAI Codex usage-limit reset) and the specific kind of answer (probability forecast over 24 and 48 hours). It is specific enough to be told apart from generic status tools, though it does not explicitly contrast with the sibling tools 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?

There is no guidance on when to use this tool instead of get_codex_status or get_reset_timeline, and no exclusions or alternative conditions are stated. The time-bound forecast wording implies a use case, but the routing decision is left entirely to the agent.

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 openWorldHint=false, so the safety profile is covered. The description adds useful return-side context — ordering (newest first), the nature of the entries, and that each carries a source URL — but says nothing about pagination behavior, result caps, or data freshness.

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 sentence that front-loads the resource and ordering. Every clause (verified, banked grants, newest first, source URL) carries information, though the parenthetical could be trimmed.

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 does the work of sketching what a record contains (dated, verified resets, grants, source URL, ordering). Combined with a fully documented input schema, an agent has enough to call it correctly, though the lack of any usage routing leaves a small gap.

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% with defaults, ranges, and enums all documented in the schema itself, so the baseline is 3. The description adds no parameter guidance; the parenthetical '(group credits)' only loosely gestures at the 'credits' enum value already listed in 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 names a specific resource ('Codex reset history') and details its contents: dated verified usage-limit resets and banked reset grants, ordered newest first, each with a source URL. It is clearly a retrospective record, which implicitly separates it from get_reset_forecast, but it never names or contrasts with that 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?

There is no when-to-use statement, no exclusion, and no pointer to the alternative tools. An agent must infer from the word 'history' that this is for retrospective lookup rather than forward-looking forecasting, which get_reset_forecast presumably handles.

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