WhatsApp Web Agent by Nova (CIVAI)

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

With no annotations provided, the description carries the full behavioral burden and discloses nothing: no permission requirements, no note on what happens if the number is already a participant or lacks a WhatsApp account, no rate-limit or privacy caveats, and no mention of side effects or return value.

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?

It is short, but this is under-specification rather than conciseness: a single noun-phrase fragment conveys no more than the tool name already does, so its brevity is not earned.

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 mutation tool with two required, fully undocumented parameters, no annotations, and no output schema, the description is missing nearly everything an agent needs: parameter formats, preconditions, side effects, error behavior, and the difference from sibling group-management tools.

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 0% for both parameters, so the description must compensate and does not. It never explains the expected format of group_id or phone_number (e.g., country-code inclusion, group JID format), leaving the agent to guess.

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 clear verb ('add') and resource ('group participant') plus platform context ('WhatsApp Web'), so the basic action is understandable. However, it is essentially a restatement of the tool name and offers no differentiation from siblings like remove_group_participant or list_group_participants beyond the obvious verb change.

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 guidance on when to use this tool versus alternatives such as create_group or remove_group_participant, nor any stated preconditions (e.g., the caller must already be an admin/member of the group). Nothing indicates when-not to use 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?

No annotations provided, so the description carries full behavioral burden. It says nothing about what 'check' entails – does it return a boolean, contact info, or a status? No mention of permissions, rate limits, or side effects. 'WhatsApp Web' gives no useful behavioral 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 words plus a platform label, but the brevity is under-specification, not efficiency. Nothing is front-loaded or useful.

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 tool with a required parameter, no annotations, no output schema, and 0% schema coverage, the description is completely inadequate. It provides no information an agent needs to call it 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 0%, and the description adds no information about the 'phone_number' parameter. It doesn't specify format (country code, digits only, E.164), or whether it's the number to check or the checker's number. With one required parameter, the description fails to compensate for the schema gap.

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 'WhatsApp Web: check number' restates the tool name with a platform prefix, adding no specific verb or resource detail. It's essentially a tautology of check_number. It could mean validate, verify registration, or check existence, but none is stated.

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?

No guidance on when to use this tool, when not to, or which alternatives to consider. Sibling tools are all about messaging and groups, so no clear routing is provided.

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?

No annotations are provided, so the description carries the full burden, and it discloses nothing: no side effects, no indication of what gets sent or opened, no auth requirements, no reversibility. An agent has no idea whether this mutates state or is a safe read.

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?

It is short, but this is under-specification rather than conciseness — the single fragment carries almost no information and does not front-load a usable verb-resource pairing.

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 tool with an undocumented parameter, no annotations, and no output schema, the description is completely inadequate. An agent cannot determine what calling it does or what a valid phone_number looks like.

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 single phone_number parameter has 0% schema description coverage, and the description adds nothing about expected format (E.164, country code, digits only) or what the number identifies. The description fails to compensate for the coverage gap.

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 'WhatsApp Web: contact about' essentially restates the tool name and adds only a platform hint. It does not state what action is performed on the contact — whether it opens a chat, initiates a conversation, or something else — so an agent cannot confidently distinguish it from siblings like converse, send_text, or check_number.

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 guidance on when to use this tool versus the many overlapping siblings (converse, send_text, reply_message, check_number). No prerequisites, no exclusions, no context of any kind.

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?

No annotations are provided, so the description carries the full burden. It says nothing about whether this ends the turn, whether it mutates state, whether it should be combined with other tool calls, or what the reply consists of — significant gaps for a tool with zero structured behavioral coverage.

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 tight sentence that front-loads the action and appends the trigger condition; nothing is wasted. It is efficient, though it is efficient at a fairly low level of detail.

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 tool is low-complexity (one optional param, no output schema), so the short description is defensible, but with no annotations and no output schema the description should at least clarify the conversational fallback's role in the turn lifecycle. It stops just short of that.

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 one optional parameter (reply_hint) whose schema description already covers it at 100% coverage, so the baseline of 3 applies. The description adds no syntax, format, or influence guidance beyond what the schema already supplies.

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?

It gives a verb ('reply conversationally') and a trigger condition ('when the request is ambiguous or needs clarification'), which separates it from the calendar siblings by function. However, the 'resource' is nebulous — there is no statement of what the reply acts on or produces, so the agent must infer it is a non-action fallback.

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 names one condition for use: ambiguity or need for clarification. It implies, but never states, that the event-management siblings (add/update/delete/check events) are the alternative when the request is clear, leaving the when-not boundary to inference.

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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing about side effects, whether participants are added at creation time, permission/auth requirements, or whether the creating account becomes admin. The only extra signal is the 'WhatsApp Web' platform tag.

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?

It is a single short fragment with no wasted words, but at this size the terseness is under-specification rather than effective conciseness. There is nothing to front-load because no substantive content is present.

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 tool is simple (one required string, one optional array), but with no annotations, no output schema, and no parameter documentation, the description leaves the agent without the minimal behavioral or parameter context needed to invoke it 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 0% for both parameters (name, participants), and the description mentions neither. It adds zero meaning about the required group name or how the participants array is interpreted.

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 concrete verb+resource ('create group') plus a platform tag ('WhatsApp Web'), so the basic action is unambiguous. However, it is essentially the tool name restated with the platform appended and offers no detail about what a created group contains or how it differs from siblings like add_group_participant.

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 when-to-use guidance, no prerequisites, and no reference to any alternative tool. An agent gets no help deciding between create_group and add_group_participant or list_group_participants.

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?

With no annotations, the description carries the full behavioral burden but only says the tool lists chats. It does not disclose whether it is read-only, whether authentication is required, how results are ordered, whether pagination exists, or what happens with default 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 text is very short, but it is a label rather than a structured description. Its brevity comes from under-specification rather than efficient communication, so it fails to front-load useful context.

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 list tool with no output schema, the description still leaves key information missing: parameter behavior, when results are empty, and any read/pagination semantics. It is not complete enough for reliable invocation without inspecting the schema.

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 description coverage for both parameters is 0%, and the description adds no meaning for 'limit' or 'search'. It does not explain filtering syntax, default limits, or what 'search' matches against, leaving the two parameters entirely undocumented.

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 ('list') and resource ('chats') and adds the platform context ('WhatsApp Web'). It is clear enough to distinguish from siblings by resource, though it does not explicitly name alternatives or differentiate further.

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?

No when-to-use guidance, no conditions for selecting this tool over alternatives like converse or list_group_participants, and no prerequisites or exclusions. Usage is only implied by the name.

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?

No annotations are provided, so the description carries the full burden, yet it discloses nothing about pagination, ordering, authentication requirements, or whether it returns admins versus members. 'List' weakly implies a read, but that is the only behavioral signal.

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 six-word description is front-loaded and waste-free, but at this length it is under-specified rather than genuinely concise; there is no filler but also no substance beyond the tool name.

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 annotations, no output schema, and a 0%-documented required parameter, the description leaves the agent without the information needed to call this tool confidently. It is too thin for a tool that must specify how to identify a group.

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 0%, so the description must compensate for the undocumented group_id parameter and does not. It never states the expected identifier format (JID, phone number, numeric ID), leaving the agent to guess.

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 clear verb+resource ('list group participants') and the 'WhatsApp Web' qualifier grounds the domain. It implicitly distinguishes itself from the add_/remove_group_participant siblings by the verb, though it never names 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?

No guidance on when to use this versus list_chats or the add/remove participant siblings, and no prerequisites or context about group membership state. The agent must infer everything from the name alone.

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?

No annotations are provided, so the description carries the full behavioral burden for a destructive mutation. It reveals nothing about required permissions, whether removal is reversible, or what happens to the group if the last participant is removed — only the bare fact that removal occurs.

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?

It is a compact, front-loaded fragment with no padding, but its brevity stems from under-specification rather than disciplined editing — it reads like a title restated rather than a description.

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 mutation tool with no annotations, no output schema, and no parameter documentation, the description omits prerequisites, side effects, and error conditions. An agent has only the task name to work from.

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 0% for two required parameters. The description implies the inputs (a group and a participant) but gives no format guidance for group_id or phone_number, which typically requires country-code/exact-format detail, so it does not compensate for the schema gap.

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+resource ('remove group participant') and the platform (WhatsApp Web), so an agent can tell it is the inverse of the sibling add_group_participant. It stops short of any explicit sibling differentiation or scope detail, but the action itself is unambiguous.

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 when-to-use guidance, no preconditions (e.g. caller must be a group admin), and no mention of the alternative add_group_participant or when removal is inappropriate. Usage is only inferable from the name.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it discloses nothing: no side effects, no authentication requirements, no indication of what happens if quoted_message_id is omitted, and no return 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?

The description is very short, but this reflects under-specification rather than economical writing. As a single fragment it is front-loaded by default but earns nothing for the agent.

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 three-parameter messaging tool with no annotations, no output schema, and no schema descriptions, the definition is wholly inadequate. An agent has no basis for choosing it over send_text or for constructing a correct reply call.

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 0% across all three parameters, and the description adds no parameter meaning at all. In particular, the role of quoted_message_id (optional reply target) versus phone_number is left completely unexplained.

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 is essentially a restatement of the tool name ('reply message') prefixed with a platform label ('WhatsApp Web'). It does not explain what replying entails versus sending a new message, nor does it distinguish this tool from the obvious siblings send_text and converse.

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 guidance on when to use reply_message instead of send_text, send_media, or converse, and no mention of prerequisites such as needing an existing message or an active chat session. The agent must infer entirely from the tool name.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about authentication requirements, rate limits, supported media types, size constraints, or what happens on success or failure.

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 extremely short and front-loaded, but it is under-specified rather than truly concise. Every word is technically efficient, yet it omits essential information an agent would need to invoke the tool correctly.

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?

Given four parameters, 0% schema description coverage, no annotations, and no output schema, the description is completely inadequate. It provides no detail about required inputs, media handling, or expected behavior beyond the bare action.

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 0% and the description adds no meaning for any of the four parameters. It does not explain the expected format of 'media_type', the role of 'media_url', the use of 'caption', or the format of 'phone_number'.

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 ('send media') and names the platform, which distinguishes it from the sibling 'send_text'. It is clear enough for an agent to understand the core action, though it lacks detail on what kinds of media are supported.

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 guidance on when to use this tool versus alternatives like 'send_text', 'reply_message', or 'converse'. The agent must infer that this is for media rather than text, but no explicit conditions or exclusions are provided.

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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not whether the number must be pre-verified (check_number exists as a sibling), not the expected phone_number format, not delivery semantics, rate limits, or side effects of sending.

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 a single short line, which is front-loaded and free of waste, but this is under-specification rather than genuine conciseness. Trimming further is impossible because almost nothing was said to begin with.

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-required-parameter action tool with no annotations, no output schema, and no parameter documentation, the description is wholly inadequate. An agent has no basis for formatting the number, expecting a response, or knowing which sibling to choose.

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 0% and the description adds no meaning for either parameter. It does not state the required format for phone_number (country code? digits only?) or any constraint on message length or content, leaving both required parameters undocumented.

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 phrase 'WhatsApp Web: send text' gives a recognizable verb and channel, but it essentially restates the tool name 'send_text' without adding scope or distinguishing it from siblings like send_media or reply_message. An agent can guess the purpose, but nothing in the text confirms what 'text' means versus a media message or a 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?

There is no when-to-use guidance whatsoever. With siblings such as send_media and reply_message available, the description never says when this tool is preferred over them, nor does it mention any prerequisites (e.g., an authenticated WhatsApp Web session).

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