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

With no annotations provided, the description carries the full burden and does state a concrete behavioral consequence: the corresponding grok_prompt call should finish with stopReason cancelled. It also discloses the notification mechanism. It stops short of describing idempotency or error behavior, but the core side effect is clear.

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 sentences with no filler. The primary action and target are front-loaded, and the second sentence adds the essential expected outcome. Every clause 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?

For a single-parameter tool with no output schema, the description covers the purpose, the trigger condition, and the resulting state change. It omits edge cases such as canceling when no turn is in-flight or idempotency, but the essential information needed to invoke the tool correctly is present.

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 sessionId as 'ACP session id whose in-flight turn should be cancelled' with 100% coverage, so the description adds no new parameter-level meaning. It simply restates the session concept from the schema, which meets the baseline but does not exceed 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 a specific verb ('Cancel'), a precise object ('in-flight prompt turn'), and the mechanism ('ACP session/cancel notification'). It clearly differentiates from sibling tools like grok_prompt and grok_session_create by targeting cancellation rather than creation, prompting, or status checks.

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 clearly implies when to use it: when a prompt turn is in-flight and should be stopped. It also explains the expected consequence on the corresponding grok_prompt call, which helps an agent reason about timing. It does not explicitly list exclusions, but there is no competing sibling tool for cancellation.

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 discloses that the tool waits for turn completion and returns aggregated text plus a tool-call summary, which is useful. However, it does not mention side effects on session state, potential long-running behavior, or how cancellation interacts with this wait, leaving some behavioral ambiguity.

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 entire description is one well-structured sentence that front-loads the core action and outcome. Every clause earns its place, and the optional includeThoughts flag is mentioned without unnecessary 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?

Given the moderate complexity, no output schema, and no annotations, the description covers the essential return values and the wait-for-completion behavior. It could go further by mentioning prerequisites or cancellation, but the parameter schema fills in the sessionId origin, and the core call sequence is clear.

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 100% parameter coverage, describing each parameter clearly, so the baseline is 3. The tool description adds minimal parameter-level meaning beyond referencing includeThoughts and the session context, which is acceptable but not especially enriching.

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 ('Send'), a clear resource (user prompt/session), and the expected outcome (return aggregated agent text plus a tool-call summary). It is easily distinguished from the sibling tools, which handle session creation, loading, cancellation, or status rather than sending prompts.

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 makes it clear this is the tool for sending a prompt and waiting for a completed turn, which implies you must already have a session from grok_session_create/load. It does not explicitly name alternatives or exclusions, but the context is strong enough that an agent is unlikely to confuse it with session management tools.

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. It does disclose that the tool creates a session and returns a sessionId, but it does not explain the surprising yoloMode default of true (auto-approve tool permissions) or any downstream effects of session creation. The schema documents the default, but the description adds little beyond the mutation and return value.

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 that front-loads the verb and purpose, names the endpoint, and states the return value. Every word earns its place with no filler.

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 2-parameter tool with a fully documented schema, the description covers the essential call semantics and return value. However, with no output schema and no guidance on session lifecycle relative to grok_session_load, an agent is left to infer when a new session is needed versus loading an existing one.

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 baseline is 3. The description adds no parameter-level detail; both cwd and yoloMode are already well-documented in the schema with meanings and defaults. The description neither compensates for gaps nor repeats schema, so baseline 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 states a specific verb and resource: 'Create a new ACP session on the local Grok Build agent (session/new).' This clearly distinguishes from siblings like grok_session_load, grok_prompt, grok_cancel, and grok_status, and even names the underlying endpoint.

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 the use case (creating a fresh session) but gives no explicit guidance on when to use this tool versus grok_session_load for existing sessions, nor any mention of prerequisites. There is clear context but no exclusions or alternatives beyond what the name conveys.

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 says 'load/resume' without explaining what that means for the agent's current session state, whether loading has side effects, whether an active session is replaced, or what happens if the sessionId is invalid. This is a significant transparency gap for a state-changing operation.

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 short sentence with no filler or redundant content. It front-loads the core action and resource, and the parenthetical protocol reference adds useful context without bloat.

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 and the schema covers both parameters, but with no annotations and no output schema, the description is the only source of behavioral context. It adequately states the purpose but leaves gaps around when to use it and what loading a session actually entails, so it is minimally viable rather than 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?

Schema description coverage is 100%, so the parameters are already fully documented in the input schema. The description adds no extra meaning about sessionId or cwd, but given the high schema coverage, the baseline score of 3 is appropriate and the description does not 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 action ('Load/resume') and a specific resource ('an existing ACP session'), making the tool's purpose immediately clear. The word 'existing' differentiates it from the sibling grok_session_create, so an agent can distinguish them 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?

Usage is only implied through the word 'existing' — an agent can infer this is for resuming prior sessions rather than creating new ones. However, there is no explicit guidance on when to use this tool versus grok_session_create, grok_prompt, grok_cancel, or grok_status, and no prerequisites or exclusions are stated.

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 state the returned fields, which implies a read-only health-check operation, but it does not explicitly confirm there are no side effects, whether it refreshes the connection, or what error behavior looks like beyond exposing lastError.

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?

One compact sentence with a colon-delimited field list. Every word earns its place and the core purpose is front-loaded.

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-parameter status tool with no output schema, the description lists the relevant return fields clearly. It leaves some ambiguity about types or structure (e.g., whether sessionIds is an array or whether connected? is a boolean), but it is largely sufficient for a simple status check.

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 tool has zero parameters, so the schema already exhaustively documents all inputs. The baseline of 4 applies, and the description does not need to add further parameter semantics.

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 ('Return') and a clear resource ('connection status'), then enumerates the exact fields returned. This makes it immediately distinguishable from the sibling action tools like grok_session_create and grok_prompt.

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 checking connection health, especially alongside action-oriented siblings, but it never states when to call it or when to prefer another tool. There is no explicit guidance such as 'use before creating sessions' or 'call this to diagnose errors.'

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