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

Annotations already declare openWorldHint=true and idempotentHint=false; the description adds the substantive consequence behind those flags — 'Messages enter the account's real conversation' — which tells the agent that every ask leaves a visible turn in real state. 'Never creates or renames bots' further constrains blast radius. It does not describe what happens to the turn if wait_seconds expires, leaving that to the 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?

Four short sentences, zero filler, with the core action and the two behavioral constraints front-loaded before the routing hint. Nothing is repeated from the schema or annotations.

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?

An output schema exists so return shape needn't be explained, and annotations carry the safety profile; what remains genuinely useful — scope, real-conversation side effect, and the check routing — is all present. A brief note on interrupt as the abort path would close the last 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 coverage is 67% and already documents agent (exact existing name, omissible) and wait_seconds (max wait, 0 returns a snapshot). The description adds meaning the schema lacks for the undocumented message parameter: 'self-contained' signals no conversational carry-over and 'one task' signals no batching in a single call.

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 precise verb and resource ('Send one self-contained task to an existing Grok Bot') and immediately bounds scope with 'Never creates or renames bots,' which separates it from the listing/creation sibling. The 'one ... task' phrasing also signals a single dispatch per call, so the agent can tell it apart from check without opening either 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?

Explicitly routes the polling case away: 'running means use check, not another ask' names both the alternative and the condition that selects it. It does not cover when to prefer interrupt, or when to omit the agent versus specifying one, so it stops short of full when/when-not coverage.

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 disclose readOnlyHint=false, openWorldHint=true, and non-idempotency, and the description is consistent with that state-mutating profile by explicitly stating that it advances this machine's cursor. 'Never resends messages' adds a valuable non-obvious guarantee about repeat behavior. What is missing is what happens when the wait times out or returns nothing.

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 compact clauses with the core action and the cursor side-effect front-loaded, and no filler. The terseness of 'wait for the previous task' is slightly ambiguous, but nothing is wasted.

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 an output schema present, the description need not explain return values, and with all parameters optional and fully documented, the remaining burden is behavioral. Cursor advancement and non-resend semantics cover the important risks for a polling tool; the gap is only timeout/empty-result behavior.

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 the agent and wait_seconds parameters are already fully documented in the schema, including the 0-means-snapshot case. The description adds only the notion of waiting for a task, which does not extend parameter meaning beyond the schema. 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 supplies the meaning the vague name 'check' lacks: it reads new replies, waits on the previous task, and advances this machine's cursor. The non-resend guarantee further pins down that only unseen messages come back. It stops short of distinguishing itself from the siblings ask, interrupt, and list, so an agent still has to infer which one to pick.

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?

'use after running or an unconfirmed send' is a concrete triggering condition, which is more than most tools offer. However, no exclusion or alternative is named, so the boundary against 'ask' or 'list' is left implicit.

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 destructiveHint=true and idempotentHint=true, but the description adds genuinely non-obvious effects: conversation and memory are preserved, and work started inside the bot's app is also halted. Only the absence of error conditions (e.g., no active turn) keeps it from a 5.

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 terse sentences, each carrying distinct information (what stops, what persists, irreversibility), with the core action front-loaded and zero 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?

An output schema exists, so return values need not be explained, and the description covers the key state consequences of interrupting. It is close to complete, though it omits what happens when no turn is active.

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 parameter with 100% schema description coverage, including the note that it may be omitted for a single configured bot. The description adds nothing about the agent parameter, so the schema-supplied baseline 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 ('Stop') and resource ('the contacted bot's current turn'), plus scope ('including work started in its app'). It is clearly distinguishable from siblings ask, check, and list, which are read/query oriented.

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 implied by the nature of an interrupt operation, and 'Cannot undo completed actions' hints at caution, but the description never states when to choose this over simply asking the bot something else or checking status first. No alternatives are named.

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=true, so the bar is lower. The description usefully adds that no message is sent and that the data is local to this machine, but says nothing about the allowlist's effect on results or what happens when the allowlist is empty.

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 compact sentences with the resource named up front and the reassurance ('sends no message') placed last where it does the most routing work. Slight awkwardness in 'existing available bots ... configured names and contacts' costs a point.

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 zero parameters and an output schema that already defines return shape, the description needs only purpose and scope, both of which are present. Only the unexplained allowlist mechanism and the lack of sibling differentiation keep it from full marks.

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 zero parameters (baseline 4), yet the description references 'the optional allowlist' as a filter with no corresponding input — likely ambient configuration. That mention is meaningful context but risks confusing an agent looking for a parameter that does not exist.

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 (list) and concrete resources (bots, configured names and contacts on this machine), which repairs the generic tool name 'list'. It does not, however, contrast itself with the siblings (check, ask, interrupt), so an agent must infer the routing.

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?

'Sends no message' implicitly steers the agent away from ask, the sibling that presumably does dispatch messages, and 'on this machine' scopes it locally. But there is no explicit when-to-use or when-not statement, and the distinction from check is left entirely to inference.

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