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

Annotations already disclose non-read-only, open-world, non-idempotent, and non-destructive behavior, so the description needn't carry the safety profile. It adds useful context by saying it waits for the agent's reply by default, though it does not explain ambiguity handling or the exact side effect of submitting an answer.

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?

Three short sentences front-load the action and input format, include a compact example, and state the default wait behavior without filler. Every sentence 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?

With full schema coverage and annotations, the definition gives enough to call the tool correctly: the action, accepted choice format, and default wait behavior are all clear. However, there is no output schema and the description does not specify what is returned when wait_for_reply is false, leaving a minor 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%, documenting all five parameters including choice format, agent matching, wait behavior, timeout, and quiet period. The description restates the choice format with examples but adds no new syntax or constraints beyond the schema, 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?

States a specific verb ('Click an option') and resource ('multiple-choice question an agent asked in Grok Bot'), with an example and input format. It distinguishes itself from a general send_message action by scoping to multiple-choice 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?

Provides clear context for when to use it: when an agent has asked a multiple-choice question. It does not explicitly name alternatives such as send_message for free-form replies or state when not to use it, but the context is unambiguous.

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 safe-read profile is structurally covered. The description adds useful behavioral context beyond that: it is a connectivity probe for the desktop app and reports the currently open chat. It does not describe error behavior or response shape, but it adds meaningful operational context.

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 short sentences, front-loaded with what the tool returns and followed by the key operational instruction. There is no filler, and every sentence contributes to correct invocation.

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 and no parameters, the description carries most of the burden for explaining what comes back. It identifies the returned entities (agents/Bots in the sidebar) and the open-chat state, and it explains the tool's role as a reachability check. It could say more about the shape of the result, but it is sufficient for a simple read-only discovery 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?

The tool takes zero parameters, so there is no parameter semantics burden on the description. Baseline for a zero-parameter tool is 4, and nothing in the description misrepresents the parameter surface.

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: 'List the agents (Bots) in the Grok Bot desktop app sidebar, and which chat is open.' It clearly distinguishes the resource and scope from siblings like read_messages and send_message, which operate on messages rather than the agent list. An agent can tell immediately what this tool returns 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?

The description gives explicit sequencing guidance: 'Call this first to check that the app is reachable.' That tells the agent when this tool is appropriate as a prerequisite or connectivity check. It does not explicitly state when not to use it or name alternatives, but the usage context is clear.

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?

Goes beyond the readOnlyHint/openWorldHint annotations by disclosing a real side effect: specifying an agent opens that chat in the app. It also tells the agent the response includes a pending multiple-choice question, which matters for follow-up calls. Ordering/pagination behavior is not covered.

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 short sentences with no filler, and the core read purpose is front-loaded ahead of the secondary open-chat behavior.

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 two-optional-parameter read tool with annotations and no output schema, the description covers what it returns (recent messages plus any pending question) and the side effect of specifying an agent. Minor gaps like message ordering are acceptable.

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%, so both parameters are already documented (prefix matching, case-insensitivity, count default/max). The description only hints at the agent parameter's effect ('opens that chat'); the baseline 3 applies since the schema carries the 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?

States a specific verb and resource ('Read recent messages from an agent chat in Grok Bot') and adds the distinguishing capability of surfacing a pending multiple-choice question. That clearly separates it from send_message and answer_choice.

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: you read messages to see what an agent said or to discover a question awaiting an answer, which routes to answer_choice. There is no explicit 'use this when' or 'do not use for' statement naming the sibling 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?

Annotations already flag non-read-only, non-idempotent, open-world behavior; the description adds genuinely useful context beyond them — that the UI visibly switches chats and types/presses Enter, and that the call blocks until the agent replies unless configured otherwise. It does not cover failure modes such as an unknown agent name or what happens if the timeout elapses.

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?

Four short sentences, front-loaded with the core action, then the visible side effect, then the return behavior, then the safety caveat. Nothing is redundant or padded.

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?

There is no output schema, and the description does the work of explaining what comes back (the agent's reply messages, possibly a multiple-choice question). Combined with the safety caveat and the blocking behavior, an agent has enough to invoke it correctly, though error/edge-case behavior is unaddressed.

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%, so agent, message, quiet_seconds, timeout_seconds and wait_for_reply are all documented in structured fields. The description only restates the default wait-for-reply behavior and mentions the reply may contain a multiple-choice question; it adds no new semantics for quiet_seconds or timeout_seconds beyond 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?

States a specific verb and resource (send a message to an agent in the Grok Bot desktop app) and further specifies the mechanism (switches chat, types, presses Enter). It implicitly distinguishes itself from read_messages and answer_choice by mentioning it returns reply messages including multiple-choice questions, but never names the siblings to route between them 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?

Gives a concrete precondition: ask the user first if the message would make the agent act outside the app, with examples (email, purchases, applications, account changes). It also clarifies default behavior (waits for the reply) so the agent knows the typical call shape. It stops short of stating when to prefer answer_choice over sending a new message.

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