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 reveals that the tool returns a sessionId and may return a status of 'awaiting_permission', which is valuable. However, it does not describe the full response structure, error handling, or any rate limits or side effects, leaving gaps in the behavior profile.

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 short sentences, each serving a distinct purpose: stating the main action, noting the return value, and giving conditional guidance. It is front-loaded with the primary purpose and avoids any redundant or filler content.

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 absence of annotations and output schema, the description covers the essential facts (session start/continue, sessionId, permission status) but is incomplete for a tool with 4 parameters and no return schema. It doesn't explain the overall response format, potential errors, or behaviors like timeouts or asynchronous execution, which are important for a chat interaction tool.

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 well-documented. The description adds little beyond what the schema states: it mentions returning a sessionId and the process for continuing sessions, but doesn't elaborate on parameter formats or constraints. This aligns with the baseline score of 3 for high 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 clearly states a specific action: 'Start a new conversation with Claude Code or continue an existing session.' It also mentions the return of a sessionId, which distinguishes it from sibling tools like get_output or list_sessions. The conditional note about 'awaiting_permission' ties it to the 'respond' tool, further clarifying its role.

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 provides explicit context for when to use the tool (starting or continuing a session) and names the alternative 'respond' for handling permission requests. It doesn't explicitly state when not to use this tool (e.g., for retrieving output), but the reference to 'respond' and the session-oriented focus give reasonable 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?

No annotations are present, so the description carries full responsibility for behavioral disclosure. It mentions cleanup and freeing resources, implying side effects, but does not state whether the action is reversible, what happens to ongoing work, or error 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, direct sentence that immediately conveys the action and its purpose. No unnecessary words or repetition.

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 one-parameter tool, the description is adequate but lacks usage context and does not clarify the distinction from sibling tools like 'interrupt'. It covers the basic function but leaves questions about when and why 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?

The input schema already documents the sole parameter with 100% coverage (sessionId: 'Session ID to close'). The description adds no extra parameter-specific meaning, so the baseline score of 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 uses a specific verb ('close') and resource ('session'), clearly stating the tool's function. It does not explicitly differentiate from sibling tools like 'interrupt' or 'list_sessions', but the primary 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?

No guidance is provided for when to use this tool versus alternatives such as 'interrupt' or 'list_sessions'. There is also no mention of preconditions or consequences that would help an agent decide between them.

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 burden. It discloses that the tool works for running or completed sessions and is non-destructive in implication, but it doesn't state whether the buffer is cleared, if it blocks, or any side effects. This is acceptable but lacks depth.

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 concise sentences that are front-loaded with the main action and then a practical use case. No unnecessary words or repetition.

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 tool is simple with one optional parameter and no output schema, so the description should clarify return values. It says 'output buffer' but does not specify the format or whether it returns all output or only new output. There is also implied default session behavior only in the schema, not the description.

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% because sessionId has a description ('Session ID (defaults to active session)'). The description adds no extra parameter information beyond what the schema already provides, so 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 clearly states the tool retrieves the current output buffer from a session, specifying both running and completed sessions. This distinguishes it from sibling tools like chat, respond, and list_sessions, which serve different purposes.

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 explicitly mentions 'Useful for checking progress,' giving clear context for when to use this tool. While it doesn't list exclusions or compare to alternatives, the purpose is distinct enough among siblings.

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. 'Get' suggests a read-only operation, but no further behavioral traits (e.g., no side effects, no network calls) are disclosed. It does not contradict anything, but it's minimal.

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 concise sentence, perfectly front-loaded with the action and resource. No wasted words.

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 simplicity (no parameters, no complex behavior), the description is sufficiently complete. It does not explain the return format, but for a version check this is generally obvious and the description covers the essential 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?

There are zero parameters, so the input schema is vacuously fully covered. The baseline for 0 params is 4, and the description adds no conflicting information.

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 ('Get') and resource ('installed Claude Code CLI version'), making its purpose crystal clear. It naturally distinguishes from sibling tools which all relate to chat/session management.

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 you need to know the CLI version) but provides no explicit context, alternatives, or when-not-to-use guidance. For a trivial version-check tool this is acceptable but still lacks the explicit guidance that would merit a higher score.

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 full burden. It discloses that the action stops a running task and is like Ctrl+C, implying a non-graceful interruption. However, it does not disclose side effects such as session state, cancellability, or reversibility, leaving significant behavioral information unstated.

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, immediately clear with a memorable analogy. It wastes no words and front-loads the core action.

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 tool is simple with one optional parameter and no output schema. The description explains the action but does not clarify relationship to sibling tools like close_session, nor the effect on the session state. It is adequate but not comprehensive.

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 provides full coverage with a description for sessionId, including its optionality and default behavior. The tool description does not add additional parameter semantics; it refers to 'task' while the parameter is 'sessionId', which may slightly conflate concepts. 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 uses specific verb 'interrupt/stop' and identifies the resource as 'currently running Claude Code task', with a helpful analogy to Ctrl+C. This clearly distinguishes from sibling tools like chat or list_sessions.

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 use when there is a currently running task that needs stopping, reinforced by the Ctrl+C analogy. It does not explicitly state alternatives or exclusions, but provides clear usage 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?

With no annotations, the description carries the burden of behavioral disclosure. It indicates a read-only action ('List') and the output ('status'), but does not mention potential limitations such as pagination, ordering, or the definition of 'active'. This is adequate but leaves gaps.

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 concise sentence, front-loaded with the action and object. Every word earns its place, with no redundant phrasing. It efficiently conveys the tool's purpose.

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, parameterless tool, the description provides the core function and output ('status'). However, it does not clarify potential edge cases like whether closed sessions are included or if there are any filters. Given the low complexity, this is fairly complete but not exhaustive.

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?

There are zero parameters, so the schema fully covers any parameter semantics. The description adds nothing beyond the schema, but no description is needed. Baseline 4 is appropriate for a parameterless tool.

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 ('List') and resource ('active sessions'), clearly indicating its function. It distinguishes from sibling tools like chat, respond, and close_session by being the only enumeration tool. The mention of 'status' clarifies the output focus.

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 on when to use this tool versus alternatives. It simply states what it does, leaving the agent to infer that it should be used when the active sessions need to be viewed. There are no exclusions or explicit alternative suggestions.

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 does well by explaining the effect of each action: 'approve' allows, 'approve_all' allows similar future operations, 'deny' rejects, and 'redirect' stops current operation and provides new instructions. This is transparent, though it omits details like session persistence or side effects beyond the immediate action.

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 extremely concise: two sentences, front-loaded with the purpose, and followed by a clean bulleted list of actions. No word is wasted, and the structure makes the action semantics easy to scan.

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 (3 params, no output schema), the description covers the main behaviors and action semantics. It lacks details about return values or what happens after the action, but for a control tool of this scope, it is reasonably complete.

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 100% description coverage, but the description adds meaningful parameter semantics by elaborating on the 'action' enum values and specifying that 'message' is required for 'redirect'. This goes beyond the schema's simple 'How to respond' and helpful for correct usage.

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 with a specific verb and resource: 'Respond to a permission request or send new instructions to Claude Code.' It lists four distinct actions that differentiate it from sibling tools like chat, interrupt, and get_output, making its role 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 provides clear context for when to use the tool—when responding to a permission request or sending new instructions. However, it does not explicitly state when not to use it or mention alternative tools, leaving some differentiation implicit rather than explicit.

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