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

With no annotations provided, the description carries the full burden. It discloses the Meta approval domain and enumerates possible status values (APPROVED, PENDING, REJECTED), but omits operational details like rate limits, authentication requirements, or error behaviors when templates are not found.

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?

Excellent structure with clear sections (purpose, usage guidance, Args, Returns). Front-loaded with the core function, zero redundant text, and appropriate use of docstring-style formatting to organize parameter and return value documentation.

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?

Appropriate for the tool's complexity (2 optional parameters, simple scalar inputs). The Returns section adequately describes the output semantics given that a formal output schema exists. Could be improved by noting error conditions or parameter validation rules.

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?

Despite 0% schema description coverage, the Args section adds crucial semantic context: template_id is explicitly identified as 'Meta template ID' (distinguishing it from internal IDs) and 'directly' implies it's the canonical identifier. However, it fails to clarify the parameter relationship (mutually exclusive vs. hierarchical) or that both are optional.

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 ('Check') and resource ('approval status of a WhatsApp template'), clearly distinguishing it from sibling tools like create_template or send_template_message which perform actions rather than status monitoring.

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?

Provides explicit temporal guidance ('Use this after creating a template') establishing the workflow sequence, and clarifies the specific value proposition ('see if Meta approved or rejected it'). Lacks explicit 'when not to use' guidance contrasting with get_template_detail.

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 disclosure burden. It successfully explains the asynchronous approval process ('go through Meta's review process') and return value structure. It could improve by mentioning idempotency concerns (duplicate names) or error behavior specifics.

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?

Well-structured with clear sections (purpose, Args, Returns). The length is justified given the complexity of the components parameter. Information is front-loaded with the core action in the first sentence, and the extensive example is essential for the nested component structure.

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 the high complexity of WhatsApp template components and the presence of an output schema (which the description briefly summarizes without redundancy), the description provides complete contextual coverage. The detailed Args example is critical for correct invocation given the lack of schema documentation.

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?

With 0% schema description coverage, the description fully compensates by providing detailed constraints for each parameter: name formatting rules (lowercase, underscores, max 512), category enums (MARKETING/UTILITY), language format examples, and a comprehensive JSON example for the complex components structure.

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 opens with a precise action ('Create and submit') and target resource ('WhatsApp template to Meta for approval'). It clearly distinguishes this from sibling tools by explicitly mentioning check_template_status as the follow-up action for monitoring the approval process.

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?

Provides clear workflow context by stating templates go through Meta's review process and directing users to check_template_status afterward. However, it does not explicitly contrast with validate_template (when to validate vs. create) or clarify failure/retry scenarios.

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 provided, the description carries the full burden of disclosure. It successfully communicates the destructive nature ('permanently deletes') and the broad scope ('ALL language variants'). It also notes the return type ('JSON confirming deletion'), though given the output schema exists, this is adequate confirmation.

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 appropriately sized with a clear structure: action statement, critical warning, parameter definition, and return type. Every section earns its place, particularly the warning which is front-loaded. The Args/Returns format is slightly formal but efficient for a single-parameter tool.

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 the tool's simplicity (1 parameter, nested objects=false) and the presence of an output schema, the description is complete. It covers the essential behavioral warning about language variants that the schema cannot express, and acknowledges the return format without needing to detail the JSON structure.

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

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

The schema has 0% description coverage (only a title). The Args section compensates by stating 'Name of the template to delete,' which clarifies the parameter's purpose beyond the schema's type information. This successfully bridges the documentation gap for the single required parameter.

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 opens with 'Delete a WhatsApp template by name,' providing a specific verb (Delete), resource (WhatsApp template), and scope (by name). The warning about deleting 'ALL language variants' further distinguishes this tool's scope from potential siblings that might handle single-language deletion.

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 WARNING section provides critical context about the irreversible scope (permanent deletion of all language variants), which guides the agent on the gravity of the operation. However, it lacks explicit guidance on when to use this vs. alternatives like update_template, or prerequisites like checking template status first.

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 full disclosure burden. It mentions the return format ('JSON with full template details'), but omits behavioral traits like error handling when a template is not found, authentication requirements, rate limiting, or whether this operation is cached vs. real-time.

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 efficiently structured with a clear first sentence summary followed by Args/Returns sections. Each sentence earns its place. The 'Returns' section is slightly redundant given the existence of an output schema, but remains useful for quick comprehension.

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 the tool has an output schema, the description appropriately does not exhaustively detail return values. However, with zero required parameters and no schema descriptions, the description should clarify the behavior when neither parameter is provided or when both are provided (error vs. precedence).

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?

With 0% schema description coverage, the description successfully compensates by documenting both parameters ('Template name to look up' and 'Meta template ID to look up directly'). It also adds the critical constraint that they are mutually exclusive, which is not captured in the schema structure.

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 clearly states the specific action ('Get full details'), resource ('WhatsApp template'), and lookup mechanism ('by name or ID'). The phrase 'full details' effectively distinguishes this from sibling check_template_status, while 'by name or ID' distinguishes it from list_templates.

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 provides critical guidance on mutual exclusivity ('Provide either... not both'), preventing invalid invocations. However, it lacks explicit guidance on when to use this versus check_template_status (status check vs. full retrieval) or list_templates (discovery vs. specific lookup).

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 provided, the description carries the full burden. It discloses pagination behavior (cursor-based via 'after') and return format ('JSON with list and pagination info'), but omits safety profile (read-only), rate limits, or error conditions.

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?

Uses efficient docstring structure with 'Args' and 'Returns' sections. Every line provides specific constraints or semantics; no redundant or filler content despite the structured format.

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 zero schema descriptions, the description adequately covers all filter parameters and pagination. With an output schema existing, the brief return description is sufficient, though it could note that all filters are optional (implied by schema but not explicit).

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?

With 0% schema description coverage, the description fully compensates by documenting all 5 parameters: 'limit' (range 1-100, default 20), 'after' (pagination semantics), 'name' (exact match behavior), and valid enum values for 'status' and 'category'.

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 clear verb ('List') and resource ('WhatsApp message templates'). Distinction from siblings (create, delete, get_detail, etc.) is implicit via the verb but lacks explicit scope clarification (e.g., which account's templates).

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?

Provides no guidance on when to use this tool versus siblings like 'get_template_detail' or 'check_template_status'. No mention of prerequisites or when listing is preferable to other operations.

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 provided, the description carries the full burden and excels by disclosing: sequential sending behavior ('one API call per recipient'), granular tracking ('Each result is tracked individually'), return structure ('JSON with per-recipient results'), and prerequisite state ('approved template').

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 uses a structured Args/Returns format that efficiently packs information without redundancy. Every sentence serves a purpose, though the structured format slightly reduces prose flow compared to integrated narrative.

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 4-parameter bulk operation tool with an output schema, the description is comprehensive. It covers all parameters, explains the sequential execution model, and describes the return format sufficiently, given that the output schema handles detailed return value documentation.

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?

Given 0% schema description coverage, the Args section compensates effectively by adding crucial constraints: country code requirement for phone numbers, default language value ('en'), and the critical constraint that components are 'same for all recipients.' Deducts one point for lack of detail on what 'components' actually contain structurally.

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 explicitly states 'Send an approved template message to multiple phone numbers,' providing a specific verb (send), resource (template message), and scope (multiple phone numbers). This clearly distinguishes the tool from the sibling send_template_message (single recipient) and links to template management siblings via the 'approved' qualifier.

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 implies usage context through 'approved template' (suggesting prerequisite validation) and 'multiple phone numbers' (suggesting bulk use), but lacks explicit guidance on when to choose this over send_template_message or warnings about rate limits despite noting sequential API calls.

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 provided, the description carries the full burden. It discloses the return value ('JSON with message ID on success') and the approval precondition, but omits safety classification (destructive/write nature), error handling behavior, rate limits, or authentication requirements.

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 docstring format with Args/Returns sections is well-structured and front-loaded with the core purpose. The components example is lengthy but necessary given the parameter's complex nested structure and lack of schema constraints; every element serves to clarify usage.

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 4 parameters and 0% schema coverage, the description adequately documents all inputs and the output format. It could be improved by mentioning error cases or explicitly contrasting with the bulk send sibling, but it covers the essential operational context.

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?

Given 0% schema description coverage, the description provides exemplary compensation with detailed Args documentation. It includes format examples (country code phone format), default values (language 'en'), and a comprehensive nested structure example for the complex 'components' parameter that clarifies the expected object shape.

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 opening sentence 'Send an approved template message to a phone number' provides a specific verb, resource, and target. It implicitly distinguishes from sibling tools by emphasizing 'approved' (contrasting with create/validate templates) and singular 'phone number' (contrasting with send_bulk_template_messages).

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 mentions 'approved template,' hinting at a prerequisite workflow involving check_template_status or validate_template, but does not explicitly state when to use this single-send tool versus send_bulk_template_messages or provide alternative selection 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?

With no annotations provided, the description carries the full burden. It successfully clarifies that this performs a rules-based validation without side effects ('before submitting'), and describes the output ('Validation result with any errors found'). Could be improved by explicitly stating this is a safe, read-only operation with no rate limit consumption.

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?

Well-structured with clear sections (purpose, usage, Args, Returns). Every sentence provides distinct value: the first defines scope, the second establishes workflow, and the Args/Returns sections document parameters. No redundancy or fluff.

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 the complexity (6 parameters including nested array objects) and complete lack of schema descriptions, the description provides comprehensive coverage. Despite the existence of an output schema, the brief Returns summary adds useful context about error-focused output without being redundant.

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?

Excellent compensation for 0% schema description coverage. The Args section provides rich semantic context for all 6 parameters: format constraints for 'name' (lowercase, underscores), valid values for 'category' (MARKETING/UTILITY) and 'template_type', examples for 'language', and structural guidance for 'components' (HEADER, BODY, FOOTER, BUTTONS).

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 clearly states the specific action (validate), target resource (WhatsApp template), and validation criteria (against Meta's rules). The phrase 'before submitting' effectively distinguishes this from the sibling create_template tool.

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

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

Explicitly states when to use the tool ('before creating a template') and establishes the workflow relationship with sibling tools. The guidance 'Use this to check for errors' clearly indicates this is a pre-flight check versus the actual creation/submission.

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