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

Annotations already declare a mutating, open-world operation; the description adds that a single threadId is shared so transcripts stay grouped, and that omitting bots fans out to every bot. That default-broadcast blast radius is meaningful behavioral context beyond the annotations. It still omits permissions 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?

Three short sentences, front-loaded with the action and followed by the two operative details (omission default and thread sharing). Nothing is padded or redundant.

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 four-parameter broadcast tool with annotations and no output schema, it covers the key call-shaping facts: fan-out scope and shared thread identity. The main remaining gap is the unexplained 'context' parameter and any permission or rate-limit 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 only 25%, and the description explains two of the four parameters: bots omission semantics and the shared threadId mechanism. 'context' and 'message' receive no explanation in either place, so the description only partially compensates for the sparse 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?

The description uses a concrete verb and resource ('Send the same message to several configured bots') and makes the broadcast scope explicit. It distinguishes itself from send_message through 'several bots' but never names the sibling, leaving that inference to the agent.

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 one conditional rule ('Omit bots to send to every bot') but says nothing about when to choose this over send_message or relay_conversation. Usage is implied rather than explicitly guided.

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 cover readOnly, idempotent, openWorld, and non-destructive behavior. The description adds useful context beyond them: polling happens once per URL, older text may appear when no timestamps exist, and inbox posts are bridge events.

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 main action is front-loaded in the first sentence, and the remaining sentences add caveats without excessive length. It is appropriately sized, with little wasted text.

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 description covers behavior and freshness caveats, and annotations plus schema cover safety and parameters. However, with no output schema, it does not explain the shape or fields of returned replies, leaving return-value context somewhat incomplete.

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 bot, limit, since, and threadId are already documented in the schema. The description adds no parameter-specific meaning beyond that baseline.

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 verbs and resources: 'Read replies already received' and 'poll each configured reply URL once.' It is clear what the tool does, though it does not explicitly distinguish itself from the sibling wait_for_reply.

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 implied usage context by saying replies are 'already received' and URLs are polled once, but it never explicitly states when to use this tool versus wait_for_reply or other siblings. The agent must infer the boundary.

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 establish that this is a safe, read-only, idempotent, non-destructive operation. The description adds useful behavioral context by stating that secrets are not included, which tells the agent the result is safe to inspect for bot discovery.

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 with no waste. The core action is front-loaded, followed by the security note and the usage trigger.

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 list tool with no output schema, the description supplies the important missing context: what is returned, that secrets are excluded, and when to use it. Nothing essential for invocation is absent.

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 parameter semantics are not a meaningful failure mode. The description correctly does not invent parameter details.

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 gives a specific verb and resource: it lists configured bots and reply channels. That is clear enough to distinguish it from the messaging siblings, but it does not explicitly contrast those alternatives.

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 states a concrete usage condition: call it when the bot id is unclear. It does not list exclusions or explicitly name alternatives, so it stops short of full when/when-not 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?

Annotations declare openWorldHint=true and readOnlyHint=false, so safety is partly covered; the description adds real value by disclosing termination behavior (maxTurns default 4, cap 20, stop_relay, human can interrupt between turns). It does not say the call blocks sequentially per reply or what happens on timeout.

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 tight sentences: purpose first, then the relay mechanism, then termination conditions. No redundant restatement of the title and nothing 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 no output schema and a non-read-only, open-world tool, the description should say what is returned (collected replies per bot?) and how threadId affects the run. It covers termination well but leaves the result shape and threading behavior unstated.

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?

Coverage is 50%; the description clarifies the roles of fromBot (receives the opening message) and toBot (receives each reply), which the schema does not. maxTurns semantics are restated from the schema, and threadId and timeoutMs are not addressed at all.

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 ("Run a multi-turn conversation between two configured bots") and explains the alternating relay mechanism, which separates it from one-shot siblings like send_message. It stops short of explicitly naming alternatives such as broadcast_message.

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: the mention of maxTurns and stop_relay tells the agent how the run terminates, but there is no explicit statement of when to choose this over send_message, broadcast_message, or wait_for_reply.

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 cover the safety profile (non-read-only, non-idempotent, open-world). The description adds the key behavioral nuance that a reply may or may not be returned synchronously, which drives the subsequent get_replies/wait_for_reply decision. It does not discuss failure modes, auth, or rate limits, keeping it just below top marks.

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 primary action, then the follow-up flow, then the continuation rule. Every sentence carries operational information 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 an async send tool with no output schema and full param coverage, the description tells the agent exactly what to expect on return and how to chain the next call via threadId. Nothing needed to invoke or follow up 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 coverage is 100%, so the baseline is 3, but the description adds real meaning about threadId semantics ('reuse threadId to continue the same conversation') that the schema only hints at with 'existing conversation id'. The 'configured bot webhook' phrasing reinforces the bot parameter's default behavior already documented in 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 a configured bot webhook') that an agent can act on directly. It differentiates itself from the read/flows siblings (get_replies, wait_for_reply) by naming them as follow-ups, though it does not explicitly contrast with broadcast_message.

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 follow-up branching: if no reply is returned, keep the threadId and call get_replies or wait_for_reply. 'Reuse threadId to continue the same conversation' clarifies the continuation case. It stops short of stating when to prefer broadcast_message or when not to use this tool.

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=false and idempotentHint=true. The description adds genuine value beyond that by disclosing the cooperative semantics — the stop takes effect only 'after the current turn,' meaning the call is not a hard interrupt. It does not say whether the call blocks until the turn ends, what it returns, or how it behaves when no relay is running.

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 with no waste, front-loaded on the action and immediately qualifying the timing of the effect. Nothing to trim and nothing important buried.

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 mutation with annotations covering the safety profile and no output schema, the description supplies the essential behavioral nuance (deferred stop). The remaining gap — error/edge-case behavior when no relay is active — is minor but real for a state-changing 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 the baseline is 4. The description correctly signals that the target is implicit (the running relay) rather than addressable by an ID, which matches the empty 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?

Names a specific verb ('stop') and a specific resource ('a running relay_conversation'), and by referencing the sibling tool by name it makes the relationship to relay_conversation explicit. An agent can distinguish this from relay_conversation, wait_for_reply, and the other messaging siblings without consulting schemas.

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 phrase 'a running relay_conversation' implies the precondition that a relay must be active, which is useful context. However, there is no explicit when-to-use guidance, no statement of what happens if called with no active relay, and no mention of alternatives (e.g., how to stop something other than a relay, or whether send_message/broadcast can terminate it).

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?

Beyond the readOnly/destructive annotations, the description discloses non-obvious behavior: default and maximum timeouts, the stale-file-is-not-a-fresh-answer rule, and the important operational constraint that 'the bot cannot push into the chat while this tool is not running.' It does not say what the tool returns on timeout (empty result vs. error), which is the remaining behavioral gap.

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?

Purpose is front-loaded in sentence one and each following sentence carries a distinct fact (timeout bounds, staleness rule, alternative tool, blocking constraint). The timeout default and maximum are restated from the schema, which is mildly redundant but useful as inline guidance.

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 seven optional parameters, the description covers the semantics an agent needs to call it correctly: wait duration limits, staleness rules, and the blocking nature of the call. The one missing piece is timeout outcome behavior (what is returned when nothing arrives), which matters for a polling 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 coverage is 100%, so the baseline is 3, but the description adds real meaning by explaining the interaction between the default ignore-existing behavior and includeExisting=true and by stating the timeout default/ceiling. It leaves ignoreExisting, since, pollIntervalMs, threadId, and bot entirely to 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?

The first sentence states a specific verb and resource with scope: 'Poll until a new reply arrives or the timeout hits.' It explicitly distinguishes itself from the read-only sibling get_replies ('call get_replies to read it'), so an agent can separate blocking-wait from fetch-now 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?

It gives an explicit routing rule: existing reply-URL text is ignored by default, and get_replies is the tool to read it; includeExisting=true opts into accepting stale content. That is clear when-to-use-which guidance. It stops short of saying when not to wait at all (e.g., prefer get_replies when a reply is known to already exist), so it is not fully exhaustive.

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