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

With no annotations provided, the description carries the full behavioral burden. It concretely states that a subprocess command (`codex doctor --json`) is executed and what areas it checks, which is useful transparency. However, it does not disclose whether the command is read-only, whether it accesses credentials or network endpoints, or what failure modes may occur.

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 compact sentence with the action front-loaded and the health categories listed efficiently. There is no filler, redundancy, or repetition of information already present 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?

The core purpose and command are clear, and the schema covers the parameters, but there is no output schema or annotation help. The description does not explain the shape of the returned JSON, exit behaviors, or potential side effects, so an agent is left to infer some important runtime context.

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 parameters (cwd, env, timeoutMs) are already fully documented in the schema. The description adds no parameter-specific meaning, which is acceptable given the high schema coverage, but it also does not improve on it.

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 the exact command (`codex doctor --json`) and the resource it operates on: Codex built-in diagnostics. It also enumerates the health domains (install, auth, config, connectivity), making it clearly distinct from siblings like codex_run or codex_login_status.

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 that this tool is for diagnosing Codex installation, auth, config, and connectivity issues, which gives the agent a clear signal about when it might be relevant. However, it does not explicitly state when to choose it over alternatives like codex_login_status or codex_help, nor does it mention when not to use it.

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 only states that the tool forks a session and optionally sends a prompt. It does not mention side effects (e.g., whether the original session is preserved, whether the new session is persisted), required permissions, network access, or what the response looks like. For a tool with 13 parameters and no annotations, this is a significant gap in transparency.

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 that front-loads the primary action and its optional variation. It is efficient and avoids redundancy. However, given the complexity of the tool (13 parameters, no annotations, no output schema), one might argue it is too terse, but as a statement of purpose it is concise without waste.

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 13 parameters, no annotations, and no output schema, the description is far too minimal. It explains only the core function and does not cover return values, edge cases, side effects, or any operational context (e.g., when to set ephemeral, how the fork interacts with session persistence). An agent would have to rely entirely on the schema and trial-and-error to use this tool correctly, which is inadequate for a complex operation.

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 input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds marginal value by mentioning the 'prompt' parameter ('optionally send a prompt'), which aligns with the schema. However, it does not provide additional context for other parameters (e.g., ephemeral, skipGitRepoCheck, dangerouslyBypassApprovalsAndSandbox) beyond what the schema already offers. The description neither compensates for any gaps nor enriches the schema's 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?

The description clearly states the tool's purpose: to fork a previous Codex session into a new session, optionally sending a prompt. It uses a specific verb ('fork'), identifies the resource (a Codex session), and distinguishes itself from siblings like codex_resume and codex_run by its focus on forking rather than resuming or running fresh. The reference to `codex exec fork` also anchors the behavior precisely.

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 gives no explicit guidance on when to use this tool versus its siblings (e.g., when to fork versus resume versus run). While the purpose is clear, it does not state conditions like 'use when you want a new session derived from an existing one' or contrast with codex_resume. The usage context is implied by the name and description but not spelled out.

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 must disclose behavior. It states the core action but does not mention output format, side effects, or handling of missing or invalid subcommands; it is acceptable for a low-risk help tool but still thin.

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, front-loaded sentence with no redundant material. Every word contributes meaning, and it is immediately scannable.

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 is sufficient for a simple no-argument invocation, but omits details like default behavior, output shape, and invalid-subcommand handling. Combined with the sparse description of 'command' and no output schema, some edge cases are left unstated.

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 already documents cwd, env, and timeoutMs, and the description adds that a subcommand is optional. However, it does not explain the expected format or values for the undocumented 'command' property, leaving a notable gap at 75% schema 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 uses a concrete verb ('Show') and names the exact resource ('Codex CLI help'), while also noting the optional subcommand behavior. It is clear on its own, though it does not explicitly contrast with sibling tools like codex_run or codex_review.

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 about when to choose help over the sibling tools or when to omit the subcommand. Usage is only implied by the word 'help,' leaving the agent to infer the triggering 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?

No annotations are provided, so the description carries the full burden of disclosing behavior. It only says 'check authentication status' and the underlying command, but it does not state whether the operation issues a network request, what its output looks like, whether it mutates state, or what happens when authentication is missing. This is minimal disclosure of behavior.

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 with no filler. It communicates the operation and the exact command reference in a compact form. 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?

Overall the tool shape is very simple: no required parameters, one clear purpose, and a generic schema. However, the description gives no indication of the response shape or success/failure semantics, and there is no output schema and no annotations to compensate. An agent can safely invoke it but may not know how to interpret the result.

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 covers all parameters (cwd, env, timeoutMs) with descriptions, so the baseline is 3. The description adds no parameter-level detail, but also none is needed because these are generic process-control parameters already well explained by 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 clearly states a specific verb and resource: 'Check Codex CLI authentication status'. It also refers to the exact underlying command (`codex login status`), which leaves no ambiguity about what the tool does. The purpose is distinct from siblings like codex_review, codex_run, and codex_doctor.

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 does not explain when an agent should call this tool instead of a sibling. No prerequisites, intended scenarios, or exclusions are provided. The usage context is left entirely to inference 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.

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

No annotations are present, so the description must carry the full disclosure burden. It reveals only that a model-override env var still applies. It does not mention that executing arbitrary arguments may have side effects, security implications, or that the process output/error format is. This is a significant gap for an escape-hatch 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, with the primary purpose front-loaded and the escape-hatch positioning in the second sentence. Every word earns its place; no fluff or redundant 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?

Despite the tool's raw nature, the description is incomplete for an agent that must call it safely. It does not state what the tool returns (stdout, exit code, etc.), whether it is synchronous, or warn about the risk of passing arbitrary args. Given no output schema and no annotations, more context is needed 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 75% (only args lacks a description). The description adds minimal meaning beyond the schema: 'arbitrary argument array' clarifies the args type but does not explain cwd, env, or timeoutMs further. Since coverage is high and the description contributes a small extra for args, a baseline 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?

States a clear verb-resource pair ('Run the Codex CLI') with a specific scope ('arbitrary argument array') and positions itself as an escape hatch relative to the other sibling tools. This distinguishes it from codex_run and the rest without needing to inspect schemas.

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 says to use it when 'options not covered by the other tools' are needed. This gives a direct condition for selection, though it does not name specific sibling tools or give excluded use cases. Still, the core guidance is unambiguous and useful.

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 must carry the behavioral disclosure burden. It only reveals that execution is non-interactive and that a new prompt may be sent; it does not disclose side effects, whether code may be executed, sandbox implications, or what happens to the resumed session. For a tool with a destructive-looking bypass parameter, this is a significant transparency 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 a single efficient sentence with no filler, and it front-loads the core operation and command. It earns its place, though it is so sparse that it leaves important behavioral and usage context unaddressed, which prevents a perfect conciseness 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?

This is a 14-parameter tool with no annotations, no output schema, and a one-sentence description. The description does not explain session selection defaults, output location, process behavior, safety posture, or relationship to the many sibling tools, so it is not complete enough for an agent to invoke it confidently in varied contexts.

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 provides 100% coverage of all 14 parameters with meaningful descriptions, so the baseline is 3. The description itself adds very little parameter-specific meaning beyond the 'new prompt' idea, but it does not need to because the schema already documents each parameter well.

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: 'Resume a previous Codex session non-interactively' and even names the underlying command `codex exec resume`. It is clearly distinct from sibling tools by mentioning 'previous session,' but it does not explicitly contrast itself with codex_run or codex_fork, so it falls just short of 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?

The description implies when to use it: when resuming a previous Codex session rather than starting a new one. However, it gives no explicit guidance about when not to use it or when to prefer a sibling tool such as codex_run or codex_fork, so the usage context is only implied.

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. It does disclose that the operation is non-interactive and scoped to the current repository, but it omits output behavior, side effects, and runtime characteristics such as session persistence or long-running process behavior.

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 with no filler. It communicates the essential operation efficiently.

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?

Despite a fully documented schema, this is a complex 16-parameter external-process tool with no annotations and no output schema. The description does not explain what the review returns, how to interpret results, or what side effects to expect, leaving significant gaps for an agent deciding whether and how to invoke it.

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 parameters are already fully documented. The description adds no parameter-level meaning, so the baseline 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 names the exact underlying command (`codex exec review`), the target (current repository), and the execution mode (non-interactive). This clearly differentiates it from siblings like codex_run and codex_raw.

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 use case is implied by the phrase 'code review', and the non-interactive qualifier suggests automated scenarios, but there is no explicit when-to-use/when-not-to-use guidance or named alternatives. An agent must infer the choice from the tool name and sibling list.

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 of behavioral disclosure. It discloses that the tool runs non-interactively and exposes 'common CLI controls', but it does not mention side effects like file modifications, sandbox behavior, approval routing, or the fact that `dangerouslyBypassApprovalsAndSandbox` exists. The schema provides some parameter-level behavior, but the description itself adds minimal behavioral context beyond the mode of execution.

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 is concise and front-loads the core purpose. It could add a bit more context about when to use it, but it is not bloated and 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?

Given the tool's complexity (17 parameters, no output schema, no annotations), the description is thin. It doesn't explain return values, side effects, or how the tool relates to codex_raw and codex_review. The schema covers parameters, but the description doesn't provide enough operational context for an agent to know what happens when the tool runs or what the output will look like.

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 schema already documents all 17 parameters. The description adds no parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate because the schema does the heavy lifting and the description doesn't need to compensate.

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 ('Run'), a specific resource ('the Codex agent'), and the mode ('non-interactively (`codex exec`)'), which clearly distinguishes it from interactive or review-oriented siblings. It doesn't explicitly name sibling alternatives, but the mention of `codex exec` and 'common CLI controls' gives enough specificity to separate it from codex_review, codex_resume, and codex_raw.

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: run the Codex agent non-interactively with CLI controls. It does not explicitly state when to use this tool versus codex_raw, codex_review, or codex_resume. The phrase 'common CLI controls' hints that codex_raw is for raw/advanced usage, but no explicit when/when-not guidance is provided.

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 transparency burden. It states the observable outcome (returning the version) but does not disclose execution details such as spawning a process, potential failures when Codex is not installed, or the output format. For a simple read-only version check 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.

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

The description is a single clear sentence with no filler. It is front-loaded with the action and object, making it immediately scannable.

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 version-check tool with no required parameters and a fully documented schema, the description is nearly complete. It lacks only minor context such as error behavior when the CLI is missing, but nothing essential to invoking the tool correctly is omitted.

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 input schema already documents all three parameters (cwd, env, timeoutMs). The description adds no additional parameter semantics, which aligns with the baseline of 3.

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 object: 'Return the installed Codex CLI version.' This clearly distinguishes it from the sibling tools, none of which are about version reporting.

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 context is implied: call this tool when you need to know the installed Codex CLI version. However, the description does not explicitly state when to use it versus alternatives or provide any exclusions, so it stops at implied guidance.

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