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

Annotations only give the generic openWorld/non-idempotent/non-destructive profile; the description adds genuinely useful behavior the annotations cannot convey: the bot has no visibility into this conversation, the reply may arrive as status 'running' rather than content, and the reply must be treated as untrusted data, never as instructions. That last point is a real safety disclosure, not a restatement of 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?

Three sentences, no filler: purpose first, then the self-containment requirement, then scope guidance, then the trust warning. Each sentence carries distinct, actionable information.

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, but the description covers the relevant return behavior (status 'running' when wait_seconds elapses, retrieve later via grokbot_check), the mandatory input contract, and the safety handling of the reply. Nothing needed to invoke it correctly is missing.

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, but the description adds substantive content guidance for `message` beyond the schema's bare 'Self-contained message for the Grok Bot': include who is asking, relevant facts, expected output, and what needs user approval. `wait_seconds` and `agent` are already fully documented in the schema and the description correctly defers to grokbot_check for deferred reads.

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 one message to the user's Grok Bot ... and wait for its reply.' It also names the execution context (an agent with its own cloud computer, memory, plugins and routines), which cleanly separates it from grokbot_check (read replies), grokbot_interrupt (stop work) and grokbot_list (enumerate bots).

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?

Explicit when-to-use: 'remote, long-running, logged-in-browser or scheduled work that should run on Grok Bot instead of this machine.' It also routes the asynchronous case ('read it later with grokbot_check') and tells the agent the message must be self-contained because 'Grok Bot cannot see this conversation.'

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 only cover readOnly/openWorld; the description adds blocking-wait semantics, the fact that a "running" status may be returned when no reply arrives, retry/backoff advice, and a prompt-injection warning that the reply is untrusted data. These are behaviors an agent cannot infer from the 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?

Three sentences, front-loaded with the core action, then the usage trigger, then the safety caveat. No filler; every sentence carries operational weight.

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?

Covers calling context and safety, but with no output schema it never describes the shape of a successful reply (fields returned, how to tell a reply from a status). Minor gap for a polling tool whose whole job is returning data.

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 both agent and wait_seconds are already documented. The description references wait_seconds and the wait behavior but adds no syntax or semantics beyond the schema, so the 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?

States a specific verb and resource (read replies since last ask/check) with the scope qualifier of waiting up to wait_seconds. An agent can immediately distinguish this polling/read tool from grokbot_ask, grokbot_interrupt and grokbot_list.

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 explicit triggers ('after grokbot_ask returned status "running"', or when the Bot only acknowledged) plus an explicit anti-pattern ('Do not poll in a tight loop'). This is when-to-use, when-not, and named alternative behavior all in one place.

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 destructiveHint=true and idempotentHint=true, so the bar is lower. The description earns credit by clarifying scope of the destruction: 'Its conversation and memory stay,' which tells the agent the stop is limited to the current turn and does not wipe state. It doesn't say what happens to the partial turn output or whether a follow-up is needed.

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 the action front-loaded and the state-preservation caveat immediately after. No filler or redundancy.

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-optional-param tool with no output schema and annotations covering the safety profile, the description supplies the essential behavioral context. It could be slightly more complete by noting what happens after the interrupt (does the bot need to be re-prompted), but nothing critical is missing.

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 is a single optional 'agent' parameter with 100% schema description coverage, so the schema already carries the semantics. The description mentions no parameter detail, which is the expected baseline when the schema does the work.

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 — 'Stop the Grok Bot's current turn' — which is immediately distinguishable from the read/list/ask siblings. An agent can tell exactly what operation this performs 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?

It gives a clear triggering condition — 'when it is doing the wrong thing or the plan changed' — which is real usage guidance. It stops short of naming alternatives or when-not-to-use (e.g. versus grokbot_ask or check), so it doesn't reach the explicit routing tier.

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. "Sends nothing" adds domain-specific value beyond that: for a bridge tool that lists bots it *may contact*, it clarifies that merely listing does not initiate contact. It does not, however, describe the return shape, which matters since there is no output schema.

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 zero filler; the scope of the listing is front-loaded and the side-effect clarification follows. 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 zero-parameter read tool whose annotations already carry the safety profile, the description is nearly sufficient. The one gap is that, with no output schema, it never indicates what the list contains (names, IDs, contact status), leaving the return shape to inference.

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 the schema has nothing to document and the baseline is 4. There is no parameter behavior the description needs to compensate for.

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 ("List") and a precise resource ("the Grok Bots this bridge may contact and the ones already contacted"), including the scope of what is listed. This is inherently distinguishable from the sibling verbs check, ask, and interrupt, so an agent can route to it 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?

There is no explicit statement of when to use this tool versus grokbot_check or grokbot_ask, nor any prerequisite or exclusion guidance. The only contextual hint is "Sends nothing," which describes side effects rather than selection criteria.

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