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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true. The description adds that messages reach customers externally or stay as internal notes, which is real behavioral context, but it never warns that retries may duplicate messages (non-idempotent) and does not disclose permission requirements or whether a sent message can later be edited or deleted.

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 purpose sentence is front-loaded and the Args/Returns/Examples structure is easy to scan. There is some redundancy since the Args block repeats schema descriptions verbatim, costing lines without adding 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?

With no output schema, the description helpfully includes a Returns line covering the created message ID and confirmation, and it covers every input with examples. Remaining gaps are edge behavior: error cases (e.g., nonexistent conversation_id) and whether the account/conversation must be accessible to the caller's token.

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 all five parameters are already documented in the schema, including the message_type enum and the private flag. The description's Args block largely restates those same definitions; the only added value is the paired worked examples, which is baseline-level supplementation.

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 ("Create a new message in a Chatwoot conversation") plus the key subtype distinction (outgoing customer message vs. private internal note). This clearly separates it from the read-oriented siblings such as chatwoot_list_messages and chatwoot_get_conversation.

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?

"This tool sends a message in an existing conversation" establishes the precondition and the two usage modes, and the two examples make the outgoing-vs-private-note choice concrete. It never states when not to use it (e.g., use chatwoot_list_messages to read existing messages instead), so it falls short of explicit alternatives.

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, and openWorld, so the safety profile is handled. The description adds genuine context beyond that by enumerating what the response contains (contact info, assignee, labels, custom attributes, message statistics), which helps the agent decide whether one call suffices.

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?

Front-loaded purpose sentence followed by sharply organized sections. There is mild redundancy in restating Args and Returns that the schema and annotations partly cover, but nothing is padded with 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?

With no output schema, describing the returned fields is the right use of space, and the description does that. It stops short of covering error behavior or what happens for a nonexistent conversation ID, but otherwise an agent has what it needs.

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 all three parameters are already documented in the schema, including the response_format enum. The Args block restates them without adding format, constraint, or failure-mode detail, so 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 ('Get detailed information about a specific Chatwoot conversation') and implicitly contrasts with chatwoot_list_conversations by scoping to a single conversation with full details. An agent can select it without ambiguity.

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 specific conversation' implies when to use it versus the list sibling, but there is no explicit when-to-use/when-not guidance, no prerequisites, and no named alternatives such as chatwoot_list_messages for message data.

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 read-only, idempotent, non-destructive and open-world. The description adds genuinely useful behavioral detail beyond that: the default status filter is 'open' (easy to miss and materially affects results), pagination is supported, and the returned fields are enumerated. It does not mention page size or total-count behavior, which keeps it at 4.

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?

Front-loaded purpose sentence, then Args/Returns/Examples in a predictable structure. The Args section duplicates every field already fully described in the schema, which is avoidable bloat, but the Returns and Examples sections earn their space.

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, the description steps in with a useful summary of returned fields (ID, status, inbox, contact, assignee, counts, timestamp). Pagination metadata and page size are the remaining unknowns, but nothing an agent needs to call it correctly 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?

Schema description coverage is 100% with enums on status, assignee_type and response_format, so the schema already carries all parameter semantics. The Args block largely restates the schema, adding only example value combinations, 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 ('List conversations from a Chatwoot account') with the scope of filtering options. It is clearly distinguishable from siblings like chatwoot_get_conversation and chatwoot_list_messages by resource, though it never names an alternative 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?

The filtering narrative plus three concrete examples ('List unassigned conversations', 'List conversations in specific inbox') give clear context for when to use it. No explicit when-not-to-use guidance or contrast with chatwoot_get_conversation, so it stops short of a 5.

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 establish that this is a read-only, idempotent, non-destructive operation. The description adds useful behavioral context by listing the returned message fields, including sender information, attachments, timestamps, and private-note flags, though it does not discuss pagination or rate limits.

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 well-organized with Args, Returns, and Examples sections, and the main purpose is front-loaded. However, the Args section largely duplicates the fully documented schema, and the Returns section is somewhat verbose for a simple read operation.

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 read-only tool with complete schema coverage and annotations, the description gives sufficient context about inputs and returned fields. The absence of pagination or volume-limit details is a minor gap, but it is otherwise complete enough for an agent to invoke correctly.

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 all three parameters are already documented in the schema. The description repeats the arguments and clarifies the response_format options, but adds little meaning beyond what the schema provides.

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 and resource: "List all messages in a Chatwoot conversation." It clearly distinguishes this from message creation and conversation-level retrieval by focusing on messages within a specific conversation, though it does not explicitly name sibling 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?

The usage context is implied by "retrieves all messages from a specific conversation" and an example is provided. However, there is no explicit guidance on when to use this instead of sibling tools such as chatwoot_get_conversation or chatwoot_create_message, and no 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?

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is carried by structured data. The description adds the snoozed/snoozed_until interaction, but says nothing about what the destructive behavior actually entails — whether resolving notifies the customer, whether the change is reversible, or what is returned.

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 purpose is front-loaded correctly in one sentence. But the second sentence ('This tool updates the conversation status') is pure restatement, and the Args section duplicates a schema that is already fully documented, so a meaningful share of the text does not earn 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 destructive, non-idempotent mutation with no output schema, an agent still lacks the side effects of each status transition and the shape of the response. Parameter coverage is complete, so this is adequate but with a clear gap around mutation consequences.

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 baseline is 3. The Args block largely restates the schema; notably it omits the schema's useful nuance that snoozing without snoozed_until lasts until the next customer reply, so it adds no meaning beyond the schema and slightly loses some.

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 ('Change the status of a Chatwoot conversation') and enumerates the four target statuses. The mutation framing makes it trivially distinguishable from the list/get/create-message siblings.

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 only guidance is the pairing rule 'use snoozed together with snoozed_until to schedule a reopen', which is genuinely useful. There is no when-to-use vs. alternatives, no prerequisite/permission context, and no statement of when not to use it (e.g., vs. merely reading or replying to a conversation).

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