Server Quality Checklist

Tool Scores

• whatsapp_send_buttonsA
  3.6/5.0
  Behavior3/5

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

  Annotations already mark this as a non-read-only, open-world operation, and the description does not contradict that. It adds the return value ('Message ID and delivery status') and the 'up to 3' limit, but does not disclose side effects, prerequisites, or error behavior, so it provides only baseline transparency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and clearly organized with an Args list and Returns line. Every sentence provides useful information, and the example JSON for buttons is immediately helpful without bloating the text.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a messaging tool with a fully documented schema, the description covers purpose, core parameters, and the return value. It lacks usage context and omits response_format from the Args list, but the schema fills most gaps, so the description remains adequate.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already documents 100% of parameters with descriptions and examples. The description repeats 'to', 'body_text', 'buttons', 'header_text', and 'footer_text' but does not add new meaning, and notably omits the response_format parameter that appears in the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The opening sentence 'Send a message with up to 3 reply buttons' uses a specific verb and resource, clearly distinguishing this from sibling send tools (text, image, list, etc.) by focusing on the interactive button format.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives no explicit guidance on when to choose this tool over siblings like whatsapp_send_text or whatsapp_send_list. It only restates the tool's purpose, leaving the agent to infer usage from the action name.

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

• whatsapp_send_contactA
  3.6/5.0
  Behavior3/5

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

  Annotations indicate readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the agent knows it is a side-effecting operation. The description adds the return value ('Message ID and delivery status') but does not disclose other behavioral traits like authentication needs, rate limits, or failure conditions. No contradiction with annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is structured as a one-sentence summary followed by a clear args list and a returns note. It is concise and easy to scan, though it somewhat duplicates schema information. No unnecessary fluff is present.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With 6 parameters and no output schema, the description provides return value information but lacks usage differentiation, error scenarios, or prerequisites. The missing 'response_format' parameter guidance also leaves a gap. Overall, it is adequate for a simple send tool but not comprehensive.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema provides full descriptions for all 6 parameters (100% coverage), so the baseline is 3. The description repeats some parameter details but omits the 'response_format' parameter entirely, and it does not add meaningful semantic value beyond the schema. The schema already explains format and constraints.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states 'Send a contact card to a WhatsApp user', specifying the verb (send) and resource (contact card). This distinguishes it from sibling tools like whatsapp_send_text or whatsapp_send_image, which serve different content types. The purpose is immediately obvious.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage for sending contact cards, but it does not explicitly state when to use this tool versus alternatives. There is no mention of exclusions or comparison to sibling send tools. The intended use is apparent from the title and name, but not explicitly guided.

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

• whatsapp_send_imageA
  3.7/5.0
  Behavior3/5

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

  Annotations already indicate readOnlyHint=false and idempotentHint=false, signaling a non-read-only, non-idempotent operation. The description adds that it returns a Message ID and delivery status, which is helpful for understanding the operation's outcome. However, it does not disclose other behavioral aspects like authentication requirements or rate limits, but these are not contradicted by annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and well-structured, using an Args/Returns format. Every line provides necessary information without fluff. It is not as minimal as a single sentence, but it avoids redundancy and fits naturally within a standard docstring.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's moderate complexity (4 parameters, no output schema), the description adequately explains the core action, parameter constraints, and return value. It lacks explicit error-handling or size-limit details, but for a straightforward send-image operation, it is sufficiently complete. The public URL requirement is a key contextual detail that is included.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  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. The description's Args section reproduces parameter meanings already present in the schema (e.g., 'to', 'image_url', 'caption'), but does not add new semantics. It notably omits the 'response_format' parameter from its Args, although the schema covers it. No additional value is provided beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states 'Send an image to a WhatsApp user via a public URL.' It uses a specific verb ('Send') and identifies the resource and medium, distinguishing it from sibling tools like whatsapp_send_text and whatsapp_send_document. The title and description align without ambiguity.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies its use for sending images, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. It does mention a key precondition: the image must be available via a public URL, which is a useful usage constraint, but there is no explicit comparison with sibling tools.

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

• whatsapp_send_reactionA
  3.8/5.0
  Behavior3/5

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

  Annotations already indicate readOnlyHint=false and idempotentHint=false, so the non-read-only nature is disclosed. The description adds the requirement that the target message must exist and states a confirmation is returned. However, it does not disclose potential side effects like overwriting a previous reaction, error conditions, or rate limits. No contradiction with annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is appropriately concise: a one-sentence summary, a compact argument list, and a single return line. It is front-loaded with the essential purpose and contains no unnecessary filler, making it easy to parse quickly.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's low complexity, the rich schema, and the annotations, the description is adequate. It covers the main purpose, the key 'existing message' constraint, and the return value. The omission of response_format in the Args list is minor since the schema fully documents it. However, it lacks explicit usage guidance and deeper behavioral details, preventing a perfect score.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has 100% description coverage, so all four parameters are documented. The description's Args list is largely redundant with the schema and omits the response_format parameter. It adds only minor context (e.g., 'Phone number of the conversation') without enhancing the overall semantic understanding beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action: 'Send a reaction emoji to an existing message.' This uses a specific verb and resource, and distinguishes it from sibling tools that send text, images, templates, etc. The title 'React to WhatsApp Message' reinforces the unique purpose.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage (reacting to an existing message) but does not explicitly contrast with alternatives such as sending a new message or other reaction-like operations. It mentions 'existing message,' which is a key prerequisite, but no exclusions or specific when-to-use guidance is provided.

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

• whatsapp_send_listA
  3.9/5.0
  Behavior4/5

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

  Annotations already indicate this is a write operation (readOnlyHint=false), and the description adds that it returns 'Message ID and delivery status,' which gives the agent a clearer expectation of the tool's outcome. It does not explicitly mention external side effects beyond sending, but the annotations (openWorldHint=true) cover the external interaction. The description provides modest additional behavioral context beyond 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured: a clear first sentence followed by an Args list and Returns line. It is relatively concise, though the Args list duplicates information already present in the schema. The structure makes it easy to scan, but the duplication could be trimmed.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the rich schema with full parameter descriptions and the presence of annotations (openWorldHint, readOnlyHint), the description covers the essential operational aspects: what the tool does, key parameters, and return value. It does not include usage timing or edge cases, but these are not critical for a straightforward send tool. The description is sufficiently complete for the agent to invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Input schema covers 100% of parameters with detailed descriptions, including examples for 'sections' and format details for 'response_format.' The description's Args list only restates parameter names and short descriptions, adding no new meaning beyond what the schema already provides. Therefore, the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with 'Send a message with a menu list of options,' which clearly identifies the tool's verb (send), resource (message with menu list), and distinguishes it from sibling WhatsApp send tools (text, image, buttons, etc.). The title 'Send Interactive List' reinforces this specific function.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description does not explicitly state when to use this tool versus alternatives like whatsapp_send_buttons or whatsapp_send_text. The use case is implied by the phrase 'menu list of options,' but there is no direct comparison or exclusion of other message types. This makes the guidance implicit rather than explicit.

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

• whatsapp_send_textA
  3.9/5.0
  Behavior4/5

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

  Annotations already indicate this is a write operation (readOnlyHint=false). The description adds meaningful context by stating the return value ('Message ID and delivery status') and documenting parameters like preview_url. It does not cover error conditions or delivery semantics, but the annotation coverage reduces the burden.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with clear sections (Args, Returns, Examples) and begins with a one-sentence purpose. It is slightly repetitive with the schema but remains concise and readable without excessive verbosity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple send-text tool with four scalar parameters and no output schema, the description provides the essential details: parameters, max length, return info, and an example. It lacks guidance on delivery status values or alternative tools, but the overall context is adequate for an agent to invoke it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so all parameters are already documented. The description repeats these details and adds an example but does not clarify response_format, which is only in the schema. It adds marginal value beyond the structured schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: 'Send a text message to a WhatsApp user.' This is a specific verb+resource combination that distinguishes it from sibling tools like whatsapp_send_image or whatsapp_send_template. The example further reinforces the core use case.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage through the title and summary but does not explicitly contrast with alternatives such as whatsapp_send_template or when to use image/document sends. The example gives a basic invocation pattern but no guidance on when this tool is preferred or deprecated.

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

• whatsapp_get_business_profileA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the list of returned fields (about, address, description, etc.) but no additional behavioral details such as permission requirements, error handling, or response_format effects.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with the purpose stated first and return fields listed clearly. Every sentence earns its place with no redundant or filler content.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple get operation with one optional parameter and no output schema, the description adequately covers the purpose and return fields. It is not exhaustive about edge cases or permissions, but the combination of annotations and sibling tool context makes the tool sufficiently understandable.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The single parameter response_format is fully documented in the schema with enum values and a description, so schema coverage is 100%. The tool description doesn't add further meaning beyond what the schema already provides, warranting the baseline score of 3.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'Retrieve' and the resource 'WhatsApp Business Profile for the configured phone number', making it distinct from the sibling tools that send messages or update the profile.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The context is clear: this is the read-only retrieval counterpart to whatsapp_update_business_profile and different from send tools. It doesn't explicitly state when not to use it, but the sibling list and 'Retrieve' phrasing make the intended use obvious.

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

• whatsapp_mark_as_readA
  4/5.0
  Behavior3/5

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

  Annotations already cover the safety profile: idempotent, non-destructive, open-world, and not read-only. The description adds the 'blue checkmarks' effect and confirms a return value. It doesn't discuss edge cases like already-read messages, but with annotations in place this is acceptable. No contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is extremely concise: two sentences plus a short args list and a return statement. The purpose is front-loaded, and every word earns its place. No redundancy or fluff.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple two-parameter tool with no output schema, the description covers the action, input, and return type. The only minor gap is the vagueness of 'Confirmation' as a return description, but this is not critical for such a straightforward operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  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. The description repeats message_id's semantics but adds no new information beyond the schema. response_format is fully documented in the schema, so the description's omission is fine.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb and resource: 'Mark a received WhatsApp message as read' and adds the observable effect ('shows blue checkmarks'). This clearly distinguishes it from sibling tools, which are all send/get/update/list operations.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description makes it clear this is for received messages (marking them as read), which is the primary usage context. It doesn't explicitly state when not to use it or name alternatives, but the sibling tools are obviously different operations, so the context is sufficient. Missing explicit exclusions prevents a 5.

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

• whatsapp_send_documentA
  4/5.0
  Behavior4/5

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

  Annotations already indicate this is a non-read-only, non-idempotent operation. The description adds valuable context: the requirement for a public URL, optional filename/caption, and a return value of 'Message ID and delivery status.' It does not contradict annotations and provides behavioral expectations beyond the safety profile.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and well-structured. The opening sentence states the core purpose, followed by a clear Args list and Returns line. No redundant text or unnecessary elaboration; every sentence contributes useful information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema, the description appropriately includes a Returns line ('Message ID and delivery status'). It covers the essential aspects: purpose, parameters, and outcome. It lacks potential error scenarios or response format details, but for a straightforward send operation with good annotations, this is sufficient. A small gap is the absence of clarification on how errors (like invalid URL) are reported, preventing a 5.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already describes all parameters. The description repeats the args list with similar wording (e.g., 'Public URL' vs schema's 'Public URL of the document to send') and does not add new semantic details beyond what the schema provides. The baseline of 3 applies because the schema carries the burden.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's action: 'Send a document (PDF, DOCX, etc.) to a WhatsApp user via a public URL.' It uses a specific verb ('send'), resource ('document'), and context ('via a public URL'), and it is distinct from sibling tools like whatsapp_send_text or whatsapp_send_image by specifying document types.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the usage context (when you need to send a document), but it does not explicitly contrast with alternatives or state when not to use this tool. The sibling tools are not referenced, so an agent must infer from the name. This meets the 'implied usage' level but lacks explicit 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.

• whatsapp_send_locationA
  4.1/5.0
  Behavior4/5

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

  Annotations already indicate a non-readonly, non-destructive operation. The description adds the return behavior ('Message ID and delivery status'), which is not in annotations or schema, and does not contradict any annotation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact but includes an Args list that duplicates the input schema. This redundancy is slightly wasteful, but the structure is clear and the content is otherwise minimal.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With a complete input schema, clear annotations, and a brief Returns statement, the tool definition covers essential use. Lack of output schema and details on delivery status prevent a higher score.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  All six parameters are fully described in the schema (100% coverage). The description's Args section repeats the same information without adding semantic detail beyond what the schema already provides, so the baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The title and description clearly state the action: 'Send a location pin to a WhatsApp user.' This is specific to location sharing and distinct from sibling tools for text, media, contact, etc., which all have different verbs and resources.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description does not explicitly compare to alternatives or state when not to use this tool, but the clear scope (location pin) implies usage context. It lacks exclusions or conditions but is clear enough for an agent to infer when it is appropriate.

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

• whatsapp_send_templateA
  4.1/5.0
  Behavior4/5

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

  Beyond the annotations (which indicate readOnly=false), the description discloses that template messages must be pre-approved and that they bypass the 24-hour window rule. This adds useful behavioral context. There is no contradiction with the annotations, and while it does not mention side effects like delivery guarantees or idempotency, it provides meaningful additional info.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with a clear first sentence, followed by Args, Returns, and an Example. It is front-loaded with the core purpose. However, the Args section duplicates schema-provided parameter details, which adds redundancy. Overall it is reasonably concise and easy to scan.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Since there is no output schema, the description appropriately defines return values as 'Message ID and delivery status'. It also includes a concrete example and the key business rule about the 24-hour window. The only notable gap is not mentioning the response_format parameter in the description, but the schema covers it, and the tool's complexity is moderate.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema has 100% coverage with detailed descriptions for all five parameters. The description's Args section largely restates the schema (e.g., to, template_name) and adds no significant new meaning. It omits response_format entirely, but since the schema already fully documents it, the description does not need to compensate. The example provides a minor mapping hint, keeping this at the baseline.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with 'Send an approved template message', a specific verb and resource that clearly distinguishes this tool from the other whatsapp_send_* siblings (text, image, document, etc.). The added detail about the 24-hour window further clarifies its unique purpose, and the example demonstrates the expected mapping for template_name and language_code.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description states 'Templates are the only way to initiate conversations outside the 24-hour window', which gives a clear when-to-use context. It indirectly implies that for in-window conversations other send tools are appropriate, but it does not explicitly name alternatives or state when-not-to-use. This is clear context without explicit exclusions.

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

• whatsapp_list_templatesA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds the env var requirement and the return structure (name, status, category, language, components), which goes beyond the annotations. No contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and front-loaded with the main verb and resource. The env var prerequisite, args, and return are all covered in a few lines without wasted words. Every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple list tool, this description is complete: it states the purpose, a critical prerequisite, the main parameters, and the return shape. The annotations cover safety, and the schema covers all parameter details. No output schema exists, but the description provides sufficient return info.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3. The description repeats limit and status semantics but omits response_format. It adds no new information beyond what the schema already provides, so no bonus beyond baseline.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb 'List' with a specific resource 'message templates' and scopes it to the WhatsApp Business Account. This clearly distinguishes it from sibling send/update/mark tools. The purpose is immediately clear.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context: it lists templates and requires the WHATSAPP_BUSINESS_ACCOUNT_ID env var. It doesn't explicitly name alternatives or exclusion criteria, but the distinction from send/update siblings is implicit and the env var prerequisite is a useful usage hint.

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

• whatsapp_update_business_profileA
  4.3/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is known. The description adds useful constraints (max lengths for about and description, websites as JSON array) and states the return is a confirmation of update. This additional detail complements the annotations without contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with an 'Args' section and a 'Returns' statement. It is concise, front-loaded with the main purpose, and every sentence provides useful information without unnecessary elaboration.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has 7 optional parameters, all fully documented in the schema, and the description covers the return value and important constraints. Annotations provide safety and idempotency context. The description is complete enough for an agent to understand when and how to use the tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the schema already documents all parameters with descriptions and constraints. The description repeats the parameter list and adds brief constraints (e.g., max lengths, JSON array), but it does not materially add new meaning beyond what is in the schema. Baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: 'Update the WhatsApp Business Profile fields.' It uses a specific verb ('Update') and resource ('Business Profile'), and the list of fields makes the scope explicit. It distinguishes itself from the sibling tool whatsapp_get_business_profile by indicating it modifies rather than retrieves.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description clearly indicates this tool is for updating profile fields and implies it should be used when those fields need modification. It does not explicitly state when not to use it or mention alternatives, but the sibling tool get_business_profile and the action word 'update' provide clear context for selection.

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