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

With no annotations provided, the description carries full burden. It discloses that the raw card is sent only to the PCI-compliant clearing provider and never stored, which is a key behavioral trait. It also implies a verification step. However, it does not mention what happens on failure, whether existing methods are replaced, or any rate limits.

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

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

Two concise sentences with the core action front-loaded. The alternative is mentioned at the end, and there is zero fluff. Every sentence contributes to the agent's understanding.

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 (nested card object, optional plan, security implications), the description covers the essential purpose, the alternative, and the security model. Missing are details about the response format or any prerequisites, but the description is sufficient for an agent to invoke it correctly with the required parameters.

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

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

Schema coverage is only 33% (only the card object is described). The description does not elaborate on the meaning of organizationName or the optional plan parameter. The card object itself is well-described in the schema, so the description adds little parameter-specific value beyond the schema.

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

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

The description states a specific action: verify a card with Tranzila and save its token to an organization. It distinguishes itself from the hosted alternative by naming the sibling tool (gambot_create_payment_link) and explaining the difference (agent vs customer entering the card).

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 provides a when-to-use scenario ('so an AI agent with the customer's card can put a payment method on file without the hosted page') and a clear alternative ('For a hosted alternative... use gambot_create_payment_link'). This leaves no ambiguity about when to select this tool.

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

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

No annotations exist, so description must carry the burden. It discloses what it checks (existence + resumability) but doesn't explain the return format, side effects (none assumed), or what 'incomplete onboarding can be resumed' implies. The 'can be resumed' is vague, leaves agent unsure what to do with the result.

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 sentences, front-loaded with the core check purpose. The 'Use before' guidance is efficient and earns its place.

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

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

No output schema and no annotations. Tool has two simple params, but the description lacks critical behavioral details: what does it return? What are the possible outcomes (exists, not exists, resumable)? What does the agent do with the result? This matters because the tool is a categorical check – without response semantics, the agent may call it but not know how to act on the result. Given the low complexity, many would be adequate, but here the missing return behavior is a real gap.

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

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

Schema coverage 50% – companyName is undocumented (just a string), but the description mentions company for input matching. companyIdNumber is documented ('9-digit company/tax id'). Description adds the purpose of combining these two fields (checking existence), but doesn't add format expectations for companyName. With 50% coverage, description partially compensates but not fully.

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?

Clear verb 'check' plus specific resource (organization) and criteria (company + tax id). Distinguishes itself from create_trial_account and other organization-related tools.

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 says 'Use before creating a new trial', which sets clear precondition. But no mention of alternatives or when NOT to use (e.g., when resuming without checking). No exclusions beyond that.

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 must disclose behavioral traits itself. It states the tool creates a campaign and mentions manual vs. scheduled execution, but it does not clarify whether creating a campaign automatically sends it or merely stores it for later execution (siblings like gambot_run_campaign and gambot_send_campaign suggest a separate step). It also omits side effects, permission requirements, or what happens on validation failure. This is a significant gap for a complex mutation tool.

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 dense but every clause earns its place, covering the main decision axes (message type, audience, scheduling) in a logical order. It front-loads the core purpose and then groups related parameters together, making it easy to scan. No redundant or filler content.

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 complexity (17 parameters, nested objects, multiple modes), the description addresses the critical branches: template vs. regular, Excel vs. ContactFilters vs. ContactsQuery, and once vs. repeated scheduling. It does not enumerate every parameter (e.g., fromNumberId, templateVariableQuery), but those are documented in the schema. The absence of an output schema is partially mitigated by the fact that creation tools typically return a campaign ID, though this is not stated. Overall, it is sufficient for an agent to make correct choices.

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 already covers 82% of parameters with descriptions, so the baseline is 3. The description adds value by explaining conditional relationships (e.g., messageType='Template' requires wabaTemplateId; messageType='regular' requires message; recipientSource='Excel' pairs with ExcelData; scheduling logic with runAt/timezone vs. interval/endCondition). These are not fully derivable from individual schema entries, so it raises the score above baseline.

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

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

The description opens with a clear verb and resource: 'Create a WhatsApp broadcast campaign.' It distinguishes itself from sibling creation tools like gambot_create_template and gambot_send_text by focusing on campaign creation, and it breaks down the core variants (manual/scheduled, template/regular) without ambiguity.

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

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

The description gives concrete guidance on parameter combinations (messageType with wabaTemplateId vs. message, recipientSource options, scheduling configuration), which effectively tells the agent how to configure the call. However, it does not explicitly mention when to prefer this tool over siblings such as gambot_run_campaign or gambot_send_campaign, nor state exclusions (e.g., 'for a single message use send_text'). The usage context is clear but alternatives are not spelled out.

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 disclosing behavior. It states the core action (creating a case) but does not mention potential side effects, validation requirements beyond the required subject, permission needs, or what response is returned. It adds only minimal input-shape context about 'customFields'.

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 front-loaded sentence with no wasted words; the core purpose appears first, followed by a clarifying parenthetical and a brief shape note. It is concise and readable. Its brevity is a strength, though it leaves semantic gaps.

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 create operation with 9 parameters, no output schema, and no annotations, this description is under-specified. It does not explain the required subject field, parameter semantics, customFields structure, or return behavior. An agent would need additional documentation or reasoning to invoke it confidently across varied inputs.

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, but it only says the tool accepts 'base fields plus a nested customFields object.' It does not explain the meaning of subject, stageId, statusId, category, priority, contactName, description, or contactPhone. The lone structural hint about customFields is helpful but far from sufficient for a 9-parameter tool.

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 and resource: 'Create a case,' and clarifies the ambiguous term with '(support ticket / פנייה)'. This distinguishes it from create tools for other resources like contacts, leads, tasks, and quotes. It does not explicitly contrast with the sibling gambot_update_case, but the create/update distinction is inherent in the verb.

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 gives no guidance on when to use this tool versus alternatives such as gambot_update_case, gambot_get_case, or other create tools. There are no explicit conditions, prerequisites, or exclusions. The intended usage is only implied by the verb 'Create'.

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 behavioral burden and does disclose a key behavior: if the phone number is already known, the tool returns the existing contact instead of creating or updating. It does not cover error behavior, permission requirements, or duplicate-matching normalization, which would be valuable for a mutation tool with no annotation 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 short sentences, front-loaded with the core behavior and then a targeted parameter pointer. There is no filler, and every clause earns its place.

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

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

Together the description and schema cover the required phoneNumber, phone-format rules, country ambiguity, duplicate behavior, and customFields key source. However, with no output schema, the description only partially explains return value (duplicate case) and says nothing about the success response shape or error conditions.

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 description adds real value beyond the schema by telling agents that custom/dynamic fields belong under customFields and pointing to gambot_get_contact_fields for the allowed keys. The schema already covers phone format, country handling, and default keys, so the remaining gaps are minor.

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 concrete operation, 'Create a contact', and adds the non-obvious idempotency behavior of returning the existing contact when the phone is already known. It is unambiguous against get/update/delete siblings, though it does not explicitly name an alternative such as gambot_update_contact.

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 creation usage and gives a valuable custom-field routing instruction with a cross-reference to gambot_get_contact_fields for valid keys. However, it does not state when to prefer this over gambot_update_contact or gambot_get_contact, so the usage boundary is implied rather than explicit.

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 must carry the behavioral burden. It discloses that it creates an instance and returns a public URL, and mentions optional pre-filling. However, it does not mention permissions, side effects (e.g., creating a persistent record), or error conditions. The core mutation is implied but not fully elaborated, leaving some behavioral gaps.

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 two sentences, front-loading the main purpose and key rationale, then adding optional parameters. It is efficient with no filler, though the parameter mention is compressed into a single clause. It remains appropriately sized and structured.

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 7 parameters, no output schema, and no annotations, the description is not complete. It does not enumerate all parameters, describe the return value beyond (a public /form/ URL), or address potential errors or prerequisites. The description covers the core idea but leaves significant gaps for even moderate complexity.

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 heavily compensate. It only mentions contactPhone, leadId, and variables explicitly, leaving language, documentName, expiresInDays, and templateId (though templateId is implied) unexplained. This is insufficient for a 7-parameter tool; the agent would lack clear definitions for several fields.

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 verb 'Generate' and resource 'distributable fill link for a document template', explaining the underlying need (templates lack static links). It differentiates from sibling tools like get_form_link or get_signature_link by focusing on document templates and fill-only instances, leaving no ambiguity about what this tool accomplishes.

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

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

It explains the context of use: 'A template has no single static link' and that this creates a fill-only instance to share with the customer. While it does not explicitly name alternative tools, the rationale guides the agent on when to invoke this tool versus others. No exclusions are provided, but the purpose is clear enough for correct selection.

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 present, the description carries full responsibility for explaining behavior. It only notes that an invoice 'draft' is created, which implies a non-final state, but it does not specify permissions, whether the operation is idempotent, what side effects occur, or what the return value is.

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 only two short sentences, front-loads the main action, and contains no filler or redundant detail. Every word serves a clear purpose.

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 create tool with a complex nested parameter and no output schema, the description is far too sparse. It does not explain what fields 'invoiceData' is expected to contain, any required invoice data, or how to find it. The agent cannot safely construct a valid request from this description alone.

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 already states invoiceData is 'Invoice fields' (100% coverage). The description's second sentence, 'invoiceData holds the invoice fields,' merely repeats that information and adds no extra meaning about required key, structure, or validation rules.

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

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

The description uses the verb 'create' and the resource 'invoice draft', which clearly states the action and object. Saying 'draft' sets it apart from sibling tools like gambot_issue_invoice and gambot_update_invoice, making its purpose 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?

The description provides no guidance on when to use this tool instead of gambot_update_invoice or gambot_issue_invoice. It does not state conditions, prerequisites, or alternatives, so an agent must infer usage 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?

With no annotations, the description carries the behavioral burden. It explicitly discloses a non-obvious side effect: 'contact created if missing'. It also surfaces the optional template-send behavior via templateMessageData factor. It does not cover auth, duplicates, or error cases, but the disclosed behaviors go well beyond the bare 'create' semantics.

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 compact sentences, front-loaded with the core action a agent needs. The side effect and optional behavior are mentioned immediately, and the cross-reference is placed at the end. No wasted words.

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?

High complexity (17 parameters, nested objects, optional template send, no output schema) but the description is minimal. It does not explain required input prerequisites beyond what the schema already provides, does not describe return values, and lacks usage context. The pointer to gambot_get_lead_fields helps but is not enough for confident invocation.

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

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

Schema description coverage is only 18%, so the description needs to compensate. It vaguely says 'Accepts all base lead fields' and points to gambot_get_lead_fields, but it does not explain the meaning of most parameters such as keys, tags, stageId, pipelineId, or priority. The parameter semantics are largely left to the agent to infer.

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: 'Create a CRM lead'. It adds meaningful scope details—contact auto-created if missing, optional template send, nested customFields—so it is clearly distinguishable from siblings like gambot_create_contact and gambot_update_lead.

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 choose this tool over alternatives such as gambot_create_contact or gambot_send_template. The reference to gambot_get_lead_fields is about parameter discovery, not usage context. There are no exclusions or conditions stated.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Create a store order' and lists body fields. It does not disclose whether the operation is idempotent, what happens on duplicate orders, whether it requires authentication or specific permissions, or what the response contains. For a mutation tool with zero annotation coverage, this is a significant gap.

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

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

The description is short and front-loaded with the action ('Create a store order'). The second sentence adds a useful hint about the body contents. It is concise and every sentence earns its place, though it could be slightly more informative without becoming verbose.

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 create operation with no annotations and no output schema, the description is incomplete. It doesn't explain the expected structure of the 'order' object, any required fields, or what the response will be. Given the tool's complexity (nested object parameter) and the lack of structured metadata, the description should provide more context for an agent 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 100% for the single parameter 'order', which is described as 'Order fields'. The description adds a little context by listing example fields (customer, items, total), but it doesn't explain the structure of the order object, required subfields, or format. Baseline 3 is appropriate since the schema already documents the 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 states a specific verb and resource ('Create a store order') and lists the body contents (customer, items, total). It is clear what the tool does. It doesn't explicitly differentiate from sibling tools like gambot_create_quote or gambot_create_invoice, but the resource name 'order' and the term 'store order' provide enough distinction.

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 versus alternatives. There is no mention of prerequisites, when an order should be created, or how it relates to other order-related tools (e.g., gambot_list_orders, gambot_update_order). The description implies usage by stating 'Create a store order' but provides no context or exclusions.

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 burden and excels: it discloses immediate billing, first charge on the next billing run, card verification with the clearing provider, token persistence, and that the raw card is never stored. It also clarifies graceful timezone/country handling, which is meaningful behavioral context beyond the schema.

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 dense but every sentence earns its place: core behavior, mandatory card semantics, use-case trigger, comparison with the trial sibling, and security guarantee. It is front-loaded with the most decision-relevant fact (straight to paid, no trial) and contains no filler.

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

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

Given a complex 9-parameter tool with no output schema and no annotations, the description is unusually complete: it covers billing behavior, security, error tolerance, and invocation context. Minor gaps remain, such as defaults for `plan`/`payEach`/`currency` and what the tool returns, but these do not severely hinder correct invocation.

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

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

Schema coverage is 56%, and the description adds significant meaning for the critical `card` parameter: it is mandatory, verified, tokenized, and not stored. It also explains companyInfo.timezone/country tolerance. However, semantics for `currency`, `simInfo`, `useCoexisting`, and `useFreeNumber` remain vague or unaddressed, with only a reference to 'same number options' as the trial tool.

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 a specific verb and resource: 'Create a new organization that goes STRAIGHT TO PAID — no free trial month.' It explicitly contrasts with the trial path, making the tool's purpose unambiguous and distinguishing it from sibling tools like gambot_create_trial_account.

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 an explicit trigger: 'Use this when an AI agent has the customer's card and should provision a paying account in one call.' It identifies the card requirement clearly, but it does not explicitly state when NOT to use this tool or point to an alternative like gambot_add_payment_method for cases where a card should be added later.

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 bears the full burden of behavioral disclosure. It explicitly states that card data is never handled by the API and that the token is saved on success, offering valuable security context. It does not cover failure modes or response specifics, but the essential process is transparent.

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 concise, two sentences, with the purpose front-loaded and no wasted words. It effectively conveys the core function and a key security trait without verbosity.

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 11 parameters, no output schema, and no annotations, the description is insufficiently complete. It explains the high-level flow but does not clarify parameter usage, prerequisites, or the response shape, leaving an agent to guess on most inputs.

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

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

Schema description coverage is only 9% (only paymentCycle has a description). The description does not compensate by explaining any parameters. With 11 parameters, the agent has no guidance on required vs. optional fields or their semantics beyond raw names, leaving significant ambiguity.

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 tool builds a secure hosted payment link (Tranzila) for adding a card to an organization. It names the specific resource ('hosted payment link') and the purpose, distinguishing it from sibling tools like add_payment_method or create_paid_account, which operate differently.

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 the use case: when you need a customer to submit card details via a hosted link. It mentions sharing the URL with the customer, which is part of the usage flow. However, it does not explicitly state when not to use it or contrast it with alternatives such as add_payment_method, leaving some ambiguity.

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 disclosing behavior. It only says 'Create a price quote,' which adds little beyond the name. It doesn't mention permissions, idempotency, side effects, or what happens on success/failure. For a mutation tool, this is a significant gap.

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

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

The description is two short sentences with no wasted words. The core purpose is front-loaded, and the parameter hint is kept brief. It is appropriately concise for a simple 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?

For a single-parameter create operation with no output schema, the description is minimally adequate but leaves out important context. It doesn't mention what the response contains, whether the quote is persisted immediately, or any validation rules. Given the lack of annotations, more detail would improve completeness.

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 already provides a description for quoteData ('Quote fields'), and coverage is 100%. The tool description adds a few example fields (title, items, total, contact), which gives slightly more context but doesn't explain required structure, nesting, or constraints. Baseline of 3 is appropriate given schema coverage and minimal added value.

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 action ('Create a price quote') with a specific resource, and the name confirms it. However, it doesn't explicitly contrast with sibling tools like create_invoice or create_order, so an agent might not immediately know the distinction without additional context. It's clear but not maximally differentiated.

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 is provided on when to use this tool versus alternatives such as create_invoice or create_order. There is no mention of prerequisites, workflow positioning, or scenarios where a quote is preferred over other document types. The agent must infer usage 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?

With no annotations, the description carries the full burden. It only says 'Create a task', implying a mutable action, but omits any side effects, permission requirements, idempotency behavior, response format, or error handling. This is a significant gap for a mutation tool.

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, concise sentence with no redundant wording. It front-loads the main action and optional link. While very short, it is appropriately sized for the primary purpose, though it could add a bit more context without losing conciseness.

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 5 parameters, one enum, and no output schema, the description is grossly incomplete. It lacks details on required fields, date formats, priority values, and what the tool returns. An agent would have insufficient information to call this tool correctly. The absence of annotations further undermines completeness.

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 only clarifies the optional contactPhone linkage. It does not explain the meaning or format of title, dueDate, priority, or description. The schema lists types but lacks descriptions, so the brief mention of contactPhone adds minimal value without compensating for the other parameters.

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 verb 'create' and the resource 'task', and adds a distinguishing detail about optional contact linking via contactPhone. This is specific enough to differentiate from siblings like update_task or list_tasks, and is not a tautology.

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 explicit guidance is provided on when to use this tool versus alternatives. The name implies creation, but there is no mention of situations where this should be preferred over update_task or any prerequisites. The usage context is left entirely 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?

With no annotations provided, the description carries the full behavioral burden. It discloses the async approval process, the strict naming constraint, and the alternative media handling (either manual header_handle injection or automatic upload via headerMediaUrl). It does not cover error handling, rate limits, or authentication requirements, but it discloses the core side effects and prerequisites.

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, tightly written paragraph. It front-loads the purpose, then moves to constraints, component types, and media handling without redundancy. Every sentence contributes essential information, making it highly efficient for an agent to parse.

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 complex tool with 7 parameters and a nested components array, the description covers the essential usage: purpose, naming, component shapes, and media options. It does not explain the response format (no output schema) or error scenarios, but it covers the main decision points. The schema's component examples fill remaining gaps, so overall it is adequately complete.

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

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

Schema coverage is 71% (5 of 7 params have descriptions), so baseline is 3. The description adds substantial value: it explains the naming format, the two media-header approaches, and the component structure with examples. This goes well beyond the schema's enum and type definitions, especially for the tricky components array.

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 verb and resource: 'Create a new WhatsApp template.' It specifies the outcome ('submitted to Meta for approval') and distinguishes this tool from siblings like list/get/delete templates by focusing on creation. The naming convention and component details further clarify its unique role.

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 gives clear context for when to use the tool and even references the sibling gambot_upload_template_media as a prerequisite for one path. However, it does not explicitly state when NOT to use this tool or contrast it with other template-related tools beyond the media upload. It implies usage but lacks explicit exclusions.

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 discloses side effects (credentials emailed/WhatsApp'd), non-hard-fail behavior for timezone/country, and post-creation steps (connect via wabaConnectUrl or gambot_exchange_waba_token). It doesn't mention reversibility or permission requirements, but the disclosed behaviors are substantial.

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 dense but well-organized: it front-loads the core purpose, then explains WhatsApp options, global fields, fallback behavior, and the alternative tool. It is longer than ideal but every sentence carries useful information, and the structure is logical.

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 complex creation tool with 8 parameters, nested objects, and no output schema, the description covers the key decision points (trial vs paid, WhatsApp number sourcing, timezone/country fallback) and post-creation next steps. It doesn't describe the return value shape, but the absence of an output schema makes that a minor gap given the rich behavioral guidance.

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 88%, so the schema already documents most parameters. The description adds meaning by explaining the WhatsApp number options (useFreeNumber, useCoexisting, BYO SIM, buy a SIM) and the global timezone/country behavior, which goes beyond the raw schema. Minor gap: plan/payEach/currency semantics are not elaborated, but the schema covers them.

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 ('Create') and resource ('a new FREE-TRIAL organization + first user'), and explicitly distinguishes it from gambot_create_paid_account. It also clarifies the no-card-required aspect, making the tool's purpose unmistakable.

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 explicitly says when to use this tool vs alternatives: 'For a paid account with a card on file (no trial) use gambot_create_paid_account instead.' It also provides clear guidance on WhatsApp number options and global fields, so an agent knows exactly when and how to invoke 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?

With no annotations provided, the description carries the full disclosure burden. It does add the valuable side effect detail that a welcome email and WhatsApp invite are sent, which is beyond the tool name. However, it omits other important behavior such as what happens to a user before they accept the invite, whether admin permissions are required, or whether this action is reversible.

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 two short sentences, each earning its place: one defines the primary action and resource, the other names the key side effects. There is no verbosity or repetition.

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 8 parameters, no annotations, and no output schema, this description is far too thin. It gives no sense of required prerequisites, invitation flow, activation status, or success/failure return information. The only added context beyond the schema are the email/WhatsApp invite mentions, which are insufficient for dependable invocation.

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

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

Schema description coverage is only 13%, so the description should compensate the missing meaning for the 8 parameters. It does not mention or explain any parameter, not even the required email or the ambiguous `role` vs `securityRole` fields. Agents are left with only the raw schema and must infer what each optional field is for.

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 the action explicitly: 'Create an organization user (team member)' with verb and resource, and adds a distinguishing behavior, 'Sends a welcome email + WhatsApp invite.' It clearly separates this from siblings like gambot_update_user or gambot_disable_user because it is the creation/invitation action.

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 is given for when to select this tool over sibling tools such as gambot_update_user, gambot_enable_user, or gambot_delete_user. The description does not cover edge cases like pre-existing users, invitations, or when an invite rather than a fully provisioned account would be expected.

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 only says 'Delete a campaign by id' with no mention that deletion is permanent, irreversible, may cascade to associated data, or require specific permissions. This is a critical omission for a destructive operation.

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 sentence that front-loads the action and resource, with no redundant words. It is perfectly concise, though this conciseness comes at the cost of substance.

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 delete tool with no annotations, no output schema, and a single parameter, the description is severely incomplete. It lacks any mention of side effects, prerequisites, confirmation steps, or error handling. An agent cannot understand the full impact of calling this tool, especially since it is destructive.

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 schema description coverage at 0%, the description must explain the parameter. It merely says 'by id', which clarifies that campaignId is the identifier but does not explain how to obtain it, its format, or any constraints. It adds minimal value beyond the schema's property name.

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 verb 'delete' and resource 'campaign', and explicitly identifies the parameter by id. It distinguishes from sibling campaign tools (get, create, update, run, etc.) because it is the only delete operation for campaigns. However, it is terse and doesn't add any nuance beyond the title.

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 is given on when to use this tool versus alternatives. It is implied that deletion is the use case, but there are no conditions, prerequisites, or exclusions. The description does not mention that deletion is irreversible or that it might be better to archive instead.

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 discloses that the operation is permanent and irreversible, which is the critical behavioral trait for a delete action. However, it does not mention potential side effects (e.g., cascading deletion of related data) or permission requirements, but the core destructive nature is well covered.

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 concise sentences with the action front-loaded and the warning/alternative immediately following. No fluff, every word earns its place.

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

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

For a simple one-parameter destructive operation, the description covers the essentials: what it does, irreversibility, and the preferred alternative. It does not describe return values (no output schema) or error conditions, but these are less critical for a delete action. The guidance is sufficient for an agent to use 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 userId parameter. The parameter name is self-explanatory, but the description does not compensate for the missing schema description, failing to add meaning beyond the bare type string.

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 tool permanently deletes an organization user, explicitly naming what is removed (auth account and profile). It distinguishes itself from the sibling gambot_disable_user by highlighting irreversibility, so an agent can immediately tell this is the destructive delete operation versus a deactivation.

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 explicitly directs the agent to prefer gambot_disable_user for deactivation, providing a clear when-not-to-use condition. It implicitly defines when to use this tool: when permanent removal is intended. This explicit routing to an alternative is strong usage 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Disable a user (status = inactive)' implies a state mutation and hints it is reversible, but does not state side effects, permission requirements, or what happens to the user's active data. For a state-changing tool with zero annotation coverage, this is a significant gap.

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

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

A single compact sentence with zero waste. The core action is front-loaded and the status detail is useful. Nothing extraneous.

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 one-parameter, no-output-schema tool, the burden is lower. The description is minimally adequate to identify the action, but lacks the usage-vs-siblings guidance and behavioral context that would make it complete.

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, but it adds no meaning for userId beyond the schema's bare 'string' type. An agent gets no hint about what identifier is expected (internal ID vs. email) or where to find it.

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

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

States a specific verb and resource: 'Disable a user'. The parenthetical '(status = inactive)' clarifies the effect, distinguishing it from delete_user (which removes) and enable_user (which reverses). Among many sibling tools, this is clear enough to tell apart.

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 enable_user, delete_user, or update_user. Given several user-management siblings, the description does not help an agent choose between them or mention that enable_user reverses this action.

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 exist, so the description carries full responsibility. It discloses the core state change ('status = active') but omits important behavioral context such as idempotency, behavior when the user is already active, permission requirements, or what the operation returns. For a mutation tool, this is a significant gap.

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

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

The description is a single front-loaded sentence with no filler or redundancy. Every word earns its place for a tool this simple.

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 one-parameter tool, the description is minimally adequate: it names the action and the resulting status. However, with no annotations and no output schema, it lacks return behavior, prerequisites, and edge-case handling, leaving the agent to guess some call-time expectations.

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 would need to compensate, but it does not mention the userId parameter at all. The parameter name is self-explanatory enough to be usable, but the description adds no meaning beyond the schema's bare 'string' type declaration.

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 action ('Enable') and the resource ('a user'), and adds the precise effect 'status = active'. This is easily distinguished from sibling tools like gambot_disable_user or gambot_update_user, whose scope is different.

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 intended use is implied by the verb and the status semantics, but there is no explicit guidance on when to use this tool versus gambot_update_user, nor any warning not to use it on already-active users. No alternatives 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?

With no annotations, the description must carry the full burden of behavioral disclosure. It discloses the actions (registers, subscribes) but omits critical details such as whether the operation is destructive, reversible, requires specific permissions, or what happens on failure. There is no mention of rate limits, idempotency, or side effects beyond the stated registration steps, leaving the agent without safety 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?

The description is concise, two sentences, with the primary action front-loaded. It avoids unnecessary words and efficiently communicates the core purpose and subsequent steps. This is appropriately sized for the complexity.

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 complexity (6 parameters, no output schema, no annotations, and low schema coverage), the description is severely incomplete. It does not describe return values, error conditions, parameter interactions, or the overall flow beyond the exchange step. An agent would struggle to understand required inputs (besides code) and expected outcomes, making this inadequate for reliable invocation.

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

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

Schema description coverage is only 17% (only 'code' is described). The description explains the 'code' parameter implicitly by referencing the authorization code, but it does not clarify the meaning or role of the other five parameters: wabaId, isCoexisting, organization, phoneNumberId, and coexistingPhoneNumber. With such low schema coverage, the description fails to compensate, leaving most parameters undefined and the tool hard to call correctly.

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, specific action: exchanging the Meta authorization code from the Facebook popup to complete embedded signup, then explicitly lists the subsequent effects (registers WABA, subscribes webhooks, registers phone number). This verb+resource is distinct from sibling tools like gambot_get_waba_connect_link, making the purpose 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?

The description implies the tool is used after obtaining the authorization code from the Facebook popup, but it does not explicitly mention prerequisites, alternatives, or when not to use it. It lacks guidance on when to choose this tool over others, though the context of 'authorization code returned by the Facebook popup' gives a clear trigger condition.

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 does disclose the key behavioral trait (appends a suffix when the base name is already taken, guaranteeing uniqueness), which is genuinely useful. However, it doesn't cover potential side effects, auth requirements, or what happens on failure. The suffix behavior is the most important trait and it is disclosed, so a 3 is appropriate.

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 efficient sentence with zero wasted words. The core purpose is front-loaded, and the uniqueness behavior is appended compactly. Every element earns its place.

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

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

For a simple 2-parameter generation tool with no annotations and no output schema, the description covers purpose, inputs, and uniqueness behavior adequately. The main gap is that it doesn't describe the return format, which the agent would need to know how to consume the result, though a name generator's output is fairly predictable.

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. It maps 'company name' to companyName and 'tax id' to companyIdNumber, clarifying their roles in the generation process. However, it doesn't add format, length, or constraint details beyond the self-explanatory parameter names. It partially compensates for the coverage gap but not fully.

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+resource: 'Generate a unique organization name from a company name + tax id'. It clearly communicates the tool's function and the uniqueness guarantee (adds a suffix if taken). It implicitly distinguishes itself from all siblings, none of which perform name generation, though it doesn't explicitly name an alternative.

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 is provided on when to use this tool versus alternatives, and no exclusions or prerequisites are stated. The description is purely functional and leaves the agent to infer appropriate usage context on its own.

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 responsibility for behavioral disclosure. It only states the action and target, without mentioning whether the operation is read-only, any permission requirements, potential side effects, or what happens if the campaign is not found. For a getter, this is a minimal disclosure but lacks depth beyond the obvious.

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 sentence with no filler. It front-loads the action and target, and the qualifier 'by id' is essential. Every word earns its place, making it exceptionally concise and well-structured.

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 get-by-ID operation with one parameter and no output schema, the description is nearly complete. It implies the return value (the campaign) and the input (the id). The lack of annotations means some behavioral context is missing, but the tool's simplicity and the clarity of 'Get a single campaign' cover the essentials. Minor gap: no mention of error behavior or pagination, but these are not critical for a single-object getter.

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 one required parameter, campaignId (type string), with 0% coverage from the description. The description's phrase 'by id' does imply campaignId is the identifier, adding slight meaning beyond the schema. However, it does not elaborate on the format, constraints, or how to obtain the ID. Since the parameter name is self-explanatory and there is only one, this is sufficient but not exceptional.

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 ('Get') and resource ('a single campaign'), and clarifies the key qualifier 'by id'. This clearly distinguishes it from siblings like gambot_list_campaigns (which retrieves multiple) and gambot_get_campaign_results (which retrieves results). The purpose is unambiguous and immediately actionable.

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 when to use this tool (when you need a specific campaign by ID) but does not explicitly state exclusions or alternatives. The name itself suggests the use case, and siblings are listed, but no explicit guidance is given about when NOT to use this vs. list or results tools. This is adequate but relies on 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?

There are no annotations, so the description carries the full behavioral disclosure burden. It does clearly imply a read-only retrieval of campaign run metricsaine, but it does not disclose response format, whether the report is generated on demand or precomputed, pagination, error behavior, or what happens if no results exist yet.

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?

One crisp sentence, front-loaded with the action and resource, and the parenthetical adds useful specificity without wasted words. No redundancy or filler.

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

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

For a simple single-parameter read tool, the description gives the core purpose and key result dimensionshare. However, with no output schema and no annotations, an agent still lacks guidance on parameter source, response shape, and edge cases like unfinished campaigns, so the definition is adequate but not complete.

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 should compensate by explaining campaignId. It does not even mention that the tool takes a campaign ID, leaving the schema property name as the only signal. The description adds no semantic detail beyond what the parameter name already reveals.

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

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

The description uses a specific verb and resource: 'Get the run results/report for a campaign,' and enumerates the exact metrics returned (sent/delivered/read/replies/clicks). This clearly differentiates it from sibling gambot_get_campaign, which would likely return campaign configuration rather than execution report data.

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 states what the tool does, but gives no guidance about when to choose it over alternatives such as gambot_get_campaign or gambot_list_campaigns. There are no prerequisites, exclusions, or context about campaign status requirements (e.g., must have been run already).

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 only states the operation ('Get') without disclosing any behavioral traits such as return format, error conditions, authentication requirements, or side effects. While 'Get' implies read-only, there is no explicit statement about that or about what the response contains.

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, direct sentence with no wasted words. It is appropriately concise for a simple getter, though it borders on under-specification. The structure is clean and front-loaded with the primary action.

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 absence of annotations and an output schema, the description is too thin to fully inform an agent. It does not describe the return value, error cases, or any nuances of retrieving a case. For a tool with a single parameter, this might be borderline acceptable, but the lack of any response information makes it insufficient for confident invocation.

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 defines a single required parameter 'caseId' with no description, and schema description coverage is 0%. The tool description does not elaborate on what 'caseId' represents, how to obtain it, or any expected format. The agent is left to infer meaning solely from the parameter name, which is minimal.

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 'Get a single case by id' clearly states the verb (get) and the resource (a single case), and distinguishes it from sibling tools like gambot_list_cases (plural) and gambot_create_case/gambot_update_case (mutations). It is not a tautology and conveys the core operation.

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. For example, it does not explain when to use get_case instead of list_cases, nor does it mention any prerequisites or context. The agent receives no direction on selection.

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 behavioral disclosure burden. It does disclose a key structural/behavioral trait: custom case values are stored under a nested 'customFields' map and must be passed the same way on create/update. However, it does not explicitly state read-only semantics, absence of side effects, or any limits/pagination, so transparency is adequate but incomplete.

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 sentences with no filler. The first sentence states the purpose and return shape; the second adds the critical customFields usage note. Every sentence earns its place, and the most important information is front-loaded.

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

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

For a zero-parameter getter with no output schema, the description is largely complete: it names the returned sections and explains the important customFields convention. It could define 'baseFields' more explicitly, but the overall complexity is low and the agent has enough to invoke the tool 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?

There are zero parameters, so there is no parameter ambiguity. The baseline for zero-parameter tools is 4, and the description adds context about the return structure without needing to explain parameters.

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-resource pair ('Get case ... field definitions') and the exact output shape ('{ baseFields, customFields }'). Adding the Hebrew term 'פנייה' removes ambiguity. It is clearly distinguishable from sibling tools like get_lead_fields and get_contact_fields because it explicitly targets cases.

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 clear context for when to use this tool: to retrieve case field definitions before creating or updating a case, especially because custom values must be passed inside a nested 'customFields' map. It does not explicitly name alternatives, but the context is strong enough for an agent to know this is the case-specific field 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 and no output schema, the description carries the full burden, but 'Fetch a contact' largely restates the tool's name and does not disclose behavior such as not-found handling, exact vs. partial match, authorization requirements, or return shape. It implies read-only, but adds little beyond the title.

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?

One sentence, front-loaded, and free of filler; every word contributes. It is appropriately sized for a simple single-parameter lookup 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?

The definition is largely complete for a one-parameter read operation: the schema fully describes the phone format, and the description states the operation and key. The absence of return-shape or not-found behavior is a minor gap given no output schema, but the simple getter context makes the tool callable without further information.

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 covers the only parameter with rich E.164/national format guidance, so the description does not need to add parameter details. It reinforces that 'phone' is the lookup key, but does not add meaning beyond what the schema already provides.

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

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

Description uses a specific verb ('Fetch'), a clear resource ('contact'), and the lookup criterion ('by phone number'), which distinguishes it from siblings such as gambot_get_contact_fields or other getters. The tool's intent is immediately actionable.

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

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

The phrase 'by phone number' gives a clear trigger condition: use this tool when you need a contact record and have a phone number. It does not enumerate when-not-to-use alternatives, but no competing get-contact-by-other-key tool exists among the siblings, so exclusions are not strongly needed.

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 burden of behavioral disclosure. It reveals the return subject (base and custom/dynamic definitions), the storage convention for custom values, and the relevant create/update field. For a no-parameter read operation, this is adequate, though it does not detail auth or response shape.

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 tight, front-loaded sentences. The first states the purpose clearly; the second adds meaningful operational context about how field definitions relate to create/update calls. No filler or redundancy.

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

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

For a zero-parameter, no-annotation getter, the description is nearly complete: it explains what is returned and how the output connects to customFields usage. The only minor gap is the lack of an exact shape for a field definition object, but the tool remains fully callable and understandable.

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 input schema is an empty object with zero parameters, so there are no parameter semantics for the description to add. It still contributes useful context about the 'customFields' key, but no parameter documentation is needed.

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: 'Get contact field definitions (base + custom/dynamic)'. It distinguishes itself from sibling tools like get_lead_fields and get_case_fields by naming the contact resource, and from get_contact by clarifying it returns definitions, not values.

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 gives clear downstream context: custom contact values are stored as top-level keys and should be passed via 'customFields' on create/update. This implies when the output matters, but it does not explicitly name alternative field-definition tools or state when not to use this one.

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 disclosing behavior. It confirms the operation is read-only by saying 'Read', but it does not disclose ordering, pagination semantics, the meaning of `after`/`before`, or how the phone number identifies a conversation.

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 clear sentence with no waste. It front-loads the core action and object, making the purpose immediately readable.

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 low schema coverage, absence of annotations, and absence of an output schema, the description is too sparse. It should compensate by explaining the `phone`-to-conversation mapping, the meaning of `after`/`before`, and pagination behavior, especially because `pageSize` has no description.

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?

Only 25% of the parameters have schema descriptions, and the tool description adds no parameter-level meaning. `after`, `before`, and `pageSize` are left entirely to their schema types, and the description does not clarify how `phone` selects a conversation or how the temporal filters interact.

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 tool's action ('Read') and resource ('message history for a single conversation'), so an agent can tell this is a read-only message retrieval tool. It does not explicitly contrast it with the adjacent `gambot_list_conversations`, but the singular 'single conversation' plus 'messages' makes the core purpose specific enough.

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 gives only a high-level purpose and no explicit guidance on when to use this tool versus alternatives such as `gambot_list_conversations` or the other `gambot_get_*` tools. It could be improved by noting, for example, that this Tool should be used when a conversation has already been identified and its full message history is needed.

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. It only restates the read operation and says nothing about the response shape, missing-template behavior, permissions, or whether the tool returns template content versus metadata.

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 only six words, front-loaded, and free of filler, which is appropriate for a simple getter. It loses a point only because the extreme brevity leaves important usage and behavioral details unstated.

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 one-parameter getter with no annotations and no output schema, the description is minimally usable: an agent can infer that templateId identifies the template to fetch. However, it does not distinguish this from gambot_get_template or indicate what the response contains.

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 does not explain templateId beyond what the property name implies. It does not specify the expected format, where the ID comes from, or how it relates to a document template.

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

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

The description uses a specific verb ('Get') and a specific singular resource ('single document template'), so the basic action is clear. However, it does not differentiate this tool from closely named siblings such as gambot_get_template or gambot_get_document_submissions.

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 instead of alternatives like gambot_list_documents, gambot_get_template, or gambot_get_document_submissions. No mention is made of prerequisites, such as how templateId should be obtained.

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 behavioral disclosure. It only states that it retrieves fill-only submissions, but doesn't mention pagination behavior, limits, error handling, or what constitutes a 'fill-only' submission. No details about response format or potential edge cases are given, leaving significant behavioral ambiguity.

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 concise sentence that front-loads the core action. It avoids verbosity and gets straight to the point. However, it is under-specified, so while concise, it sacrifices essential details.

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 absence of an output schema, annotations, and parameter descriptions, this tool is incompletely specified. The description doesn't explain what the submissions contain, how they are returned, or any constraints (e.g., time range, ordering). For a tool with only two parameters, an agent needs more context to use it correctly, especially since sibling tools like gambot_get_form_submissions may have richer descriptions.

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%, meaning the description adds no meaning to the parameters. The description doesn't explain what templateId refers to (beyond the obvious) or what the limit parameter controls (e.g., default value, maximum behavior). The agent must rely solely on the parameter names and types, which is inadequate for correct invocation, especially for the optional limit.

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 a specific verb ('Get'), a specific resource ('fill-only submissions'), and its source ('document template'). It distinguishes itself from generic submission retrieval by specifying 'fill-only' and 'document template', which helps differentiate from sibling tools like gambot_get_form_submissions. However, it does not explicitly name the alternative, so it falls short of a perfect score.

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 no guidance on when to use this tool versus alternatives. It doesn't mention conditions, exclusions, or reference any sibling tools. An agent would have to infer usage context from the name alone, which is insufficient for a tool with many similar getters.

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 only states the basic retrieval action and gives no detail about what the definition contains, whether the operation has side effects, what errors may occur, or what the response looks like. The verb 'Get' implies read-only behavior, but that is not made explicit.

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 concise sentence with no filler or repetition. It front-loads the core action and resource. It is appropriately brief for such a simple single-parameter tool, though it could have used the space to add more behavioral or parameter 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 tool with no annotations, no output schema, and no parameter description, the definition is under-specified. The agent is left without information about the return value, possible failure modes, or how formId should be supplied. More context is needed for reliable invocation.

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%, yet the description adds no meaning about the formId parameter beyond what its name implies. It does not explain how to obtain formId, its format, or its role in retrieving the definition. With no schema description and no parameter detail in the tool description, the agent gets minimal semantic help.

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

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

The description uses a specific verb ('Get') and resource ('single web form definition'), clearly indicating this tool retrieves one form by ID. The word 'single' differentiates it from gambot_list_forms, and 'definition' separates it from form links or submissions. This is clear, though it does not explicitly name sibling alternatives.

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

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

There is no guidance about when to use this tool versus siblings like gambot_list_forms, gambot_get_form_link, or gambot_get_form_submissions. No prerequisites, alternatives, or exclusions are mentioned. Usage is only weakly implied by the phrase 'single web form definition.'

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 must convey the behavioral profile. It discloses that the link is stable and public, and that submissions land in the form's submissions. This adds useful context beyond what a simple 'Get link' would imply. However, it doesn't cover error conditions, required permissions, or the response format, leaving some gaps for an agent to infer.

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 exactly two sentences with no filler. The first sentence states the core action, and the second adds usage context and a behavioral detail. It is front-loaded and every word earns its place, making it a model of concise 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 that the tool is a simple getter with one parameter and no output schema, the description covers the main aspects: what it does, how to use the result, and a key behavioral property. It lacks details on the response structure or error handling, but these are not critical for such a straightforward tool. Overall, it is sufficiently complete for an agent 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?

The schema has a single required parameter 'formId' with 0% description coverage. The description never mentions formId or explains how it relates to the form. While the parameter name is self-explanatory and the description refers to 'a web form', it fails to explicitly state that formId identifies that form, which is a missed opportunity to add semantic value.

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 'Get the stable public shareable link for a web form', specifying a verb and resource. It distinguishes from siblings like gambot_get_form and gambot_get_form_submissions by focusing on the public link, and even elaborates on its distribution purpose. This leaves no ambiguity about what the tool does.

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 gives a clear context for when to use the tool: 'Distribute it to customers via WhatsApp/email/SMS/QR'. It implies that this is for sharing a form link, and clarifies that submissions go to the form. While it doesn't explicitly name alternatives or state when not to use it, the intended scenario is evident and easy to follow, especially with sibling tools that retrieve forms or submissions.

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 present, so the description must disclose behavior. It only says 'Get submissions' and does not mention pagination behavior, how `limit` affects results, default ordering, response shape, or error conditions. For a retrieval tool this is a mild but real transparency gap.

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

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

The description is a single, front-loaded sentence with no filler. The parenthetical '(results)' usefully clarifies that 'submissions' refers to the submitted data. All words earn their place.

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

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

For a simple get-by-form operation with two parameters and no output schema, the description is minimally sufficient: it names the resource and what is returned. Still, it omits practical context like pagination/default ordering and how `limit` interacts with retrieval, leaving an agent to infer behavior.

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

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

Schema description coverage is 0%, and the description does not explain either `formId` or `limit` beyond the raw schema. The description adds no parameter meaning; it does not state that formId identifies the web form, that limit caps returned results, or what the limit's maximum of 5000 implies.

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

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

The description uses a specific verb ('Get') and a specific resource ('submissions (results) for a web form'). This clearly distinguishes it from siblings like gambot_get_document_submissions and gambot_get_form because it targets web-form submissions rather than document submissions or form metadata.

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 clearly implies when to use this tool: whenever submission results for a web form are needed. However, it does not explicitly state when not to use it or mention alternatives such as gambot_get_document_submissions, so the guidance is adequate but implicit.

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 behavioral burden. 'Get' clearly implies a read-only operation, but the description does not disclose response shape, error behavior, permissions, or whether the full invoice object is returned.

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

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

The description is a single short sentence with no filler. The key information is front-loaded and the phrasing is appropriately compact for a simple one-parameter getter.

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

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

The description is adequate for a simple one-parameter retrieval tool, but with no output schema and no annotations, the agent is left to assume the return object and error behavior. A brief note about the response would make it complete.

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 only parameter invoiceId has no description. Saying 'by id' adds minimal meaning beyond the property name, but it does not specify the expected identifier format or how to obtain it, so the description does not sufficiently compensate.

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 action (Get), the resource (invoice), and the selection mechanism (single by id). It is distinct from list_invoices and update_invoice, though it does not explicitly name those sibling tools.

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 gambot_list_invoices or gambot_update_invoice. 'Single' implies a one-record fetch, but the agent must infer the appropriate context without explicit direction.

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?

There are no annotations, so the description carries the full burden. 'Get' clearly communicates a non-mutating read operation, and 'by id' indicates the selection mechanism. Still, it does not disclose error behavior, authorization requirements, or response shape, leaving some behavioral details implicit.

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 front-loaded sentence with no filler or redundant phrasing. It immediately conveys the essential operation and is appropriately sized for a simple one-parameter lookup 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?

For a one-parameter read operation, this definition is workable: the resource, ID parameter, and read semantics are clear. However, with no annotations and no output schema, the description leaves return format and edge-case behavior to the agent's assumptions, making it adequate but not complete.

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 only defines leadId as a required string; the description's 'by id' tells the agent that leadId is the identifier used to look up the lead. This adds a bit of meaning beyond the schema, but the description does not provide format, source, or additional constraints, and schema description coverage is 0%.

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 action ('Get'), a resource ('a single lead'), and the lookup method ('by id'). This makes it clear that the tool retrieves one lead rather than listing leads, and it is distinguishable from siblings like gambot_list_leads and gambot_get_lead_fields, though it does not name 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?

The usage context is implied: use this when you have a specific lead ID and need that single lead. However, the description gives no explicit when-to-use/when-not-to-use guidance or alternatives, so the agent must infer the appropriate choice from the name and schema.

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 behavioral disclosure burden and does a solid job: it explains that custom lead values are stored under a nested 'customFields' map and that the same structure must be used on create/update. It does not explicitly state that the call is read-only, but the tool name and lack of parameters make that reasonably clear.

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 two tight sentences with no filler. The core purpose is front-loaded, and the nested customFields guidance earns its place by preventing a common create/update mistake.

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 parameterless getter with no output schema, the description is complete: it names the response components, explains the nested structure, and connects that structure to related create/update tools. There are no missing inputs to clarify and no output schema to compensate for.

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

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

The tool has zero parameters, so the baseline is 4; there is nothing the description needs to clarify about inputs. The description instead adds value by explaining the semantic structure of the returned fields, which is more useful than repeating parameter schema information.

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: retrieving lead field definitions, and it specifies the exact returned shape as { baseFields, customFields }. It is clearly distinguishable from sibling tools like gambot_get_lead (retrieving a lead record) and gambot_get_contact_fields (different entity) without needing to open schemas.

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

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

The description implies usage by noting that custom field values must be passed the same way on create/update, which tells the agent when the returned definitions are relevant. However, it does not explicitly say when to prefer this tool over alternatives or mention any exclusion criteria.

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 burden of behavioral disclosure. It does communicate a read-only, single-result operation, but it says nothing about not-found behavior, return structure, idempotency, or any side effects. The behavioral info is minimal.

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 front-loaded sentence with zero filler. Every word contributes to the tool's core purpose, which is appropriate for such a simple one-parameter getter.

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 trivial one-parameter read operation, the description is minimally viable: the agent knows what to call and which argument is required. However, it lacks any mention of output shape, error cases, or distinction from list_orders, so it is not fully complete for an agent navigating many sibling 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%, so the description must compensate. It only restates that the order is fetched 'by id' and adds no meaning beyond the parameter name 'orderId' already present in the schema. No format, source, or validation context is provided.

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

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

The description uses a specific verb and resource: 'Get a single order by id.' It clearly distinguishes this from list_orders, update_order, and other order-related tools while matching the get-by-id pattern of sibling tools.

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 gives no explicit guidance on when to use this tool versus list_orders or other alternative tools. It implies a single-order lookup but never states exclusions or conditions, leaving the agent to infer the appropriate context.

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 must carry the behavioral disclosure burden. It only conveys a read-style operation through the word 'Get' and says nothing about response format, not-found behavior, permissions, or potential side effects.

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?

One short, front-loaded sentence with no filler. It conveys the essential operation efficiently.

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 and the description is enough to make a plausible call with quoteId, but there is no output schema, no annotations, and no guidance on where quoteId comes from or what the response contains. For a get-by-id tool this is barely adequate.

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 only parameter has no description. The phrase 'by id' adds only minimal semantic weight because the parameter name quoteId is already self-describing; no format, source, or example is given.

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 action ('Get'), a clear resource ('a single quote'), and the retrieval key ('by id'). It is distinguishable from list_quotes by the 'single' qualifier, though it does not explicitly name sibling alternatives.

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

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

There is no guidance about when to use this tool instead of list_quotes, update_quote, or create_quote. The only implied context is that you already have a quoteId, but no when-not-to-use or alternative 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?

With no annotations provided, the description carries full behavioral burden. It states it includes signing results, which is useful, but does not disclose whether the operation is read-only, requires specific permissions, or what happens if the document is not found. It fails to mention any side effects or limitations.

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 concise and front-loaded: it states the primary function and a key detail (signing results). No fluff or redundancy.

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?

As a simple get-by-id tool with one parameter required allem in schema, the description is minimally sufficient to understand the basic operation Dove. However, given no output schema and no annotations, adding context about response format or errors would improve completeness.

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

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

Schema coverage is 0%, so the description must explain the parameter. It does not elaborate on the documentId format (e.g., is it a UUID?) or any constraints. The name implies the documentId identifies the signature document, but that is minimal.

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 it retrieves a single e-signature document with its signing results, using a specific verb 'Get' and resource 'e-signature document'. It distinguishes from siblings like gambot_list_signatures (list all) and gambot_get_signature_link (get link), though it doesn't explicitly name them.

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 it is used for retrieving a specific signature document by ID, given the required documentId parameter. However, it does not explicitly state when to use this over siblings like gambot_list_signatures or gambot_get_signature_link, nor provide any alternative context.

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 behavioral burden. It adds context ('existing signature document', 'one per signer') that suggests a non-destructive read operation, but it does not disclose whether the call generates or refreshes links, whether there are side effects, permissions required, or the structure/expiration of the returned links. This is adequate but leaves notable gaps.

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 two sentences of high efficiency: the first states the primary function and the second advises the sharing workflow. There is no fluff, and the key details are front-loaded. The word 'signature' appears three times, but the brevity justifies it.

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 single-parameter tool with no output schema, the description covers the general purpose and output shape (links, one per signer) but does not specify the output type (string vs list) or any error conditions. The essential workflow is clear enough for an agent, yet the missing structural details prevent a higher score.

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 only lists documentId as a string with 0% description coverage. The description indirectly refers to it as an existing signature document, but does not explain how to obtain it, what happens if it is invalid, or any additional context needed. With only one parameter, this lack of clarification weakens the description's value.

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

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

The description uses a specific verb ('get') and resource ('signing link') for existing signature documents, and even clarifies the link distribution is one per signer. This distinguishes it from siblings like gambot_get_form_link and gambot_create_document_link, leaving no ambiguity about what this tool returns.

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 gives a clear context: acquire links to distribute an existing signature document to signers via WhatsApp/email/SMS. It does not, however, explicitly mention when not to use it or compare it to alternative tools like gambot_create_document_link or gambot_get_form_link, so it stops short of offering exclusions.

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 conveying behavior. 'Get' clearly indicates a read operation and implies non-destructive behavior, but the description does not disclose what happens for missing IDs, authorization requirements, or response shape. This is acceptable for a simple get-by-id tool but not richly transparent.

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, front-loaded sentence with no filler. Every word adds meaning: 'Get' states the action, 'single task' states the resource scope, and 'by id' states the lookup key. It is concise without being under-specified.

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 one required parameteraine and no output schema, the description is largely sufficient: the agent knows what action to take and which parameter to fill. It does not cover edge cases like task-not-found or authorization, but given the low complexity of a single-id lookup, the missing information is relatively minor.

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. It adds 'by id,' which maps directly to the taskId parameterBern, but it does not explain the format, expected value semantics, or any constraints beyond the schema's required field declaration. The parameter name is self-explanatory, but the description provides minimal additional meaning.

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

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

The description uses a specific verb and resource: 'Get a single task by id.' It clearly states the tool returns one task rather than a list, which distinguishes it from list_tasks, create_task, and update_task. The phrase 'single' and 'by id' adds precision beyond the title.

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 the appropriate use case: retrieving exactly one task when the task ID is known. It does not explicitly name alternatives or exclusions, but the 'single task by id' wording provides clear context for when this tool should be selected over list_tasks or update_task.

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 present, the description carries the behavioral burden. It communicates that this is a read operation (get) and that the result includes Meta approval status, which is useful. However, it does not disclose authentication needs, error behavior, or response format implications.

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, front-loaded sentence with no filler. It communicates the core operation and a valuable extra detail compactly.

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 get-by-id tool with one required parameter, the description is mostly adequate. However, with no output schema and no mention of response shape or where the template ID comes from, an agent still has meaningful gaps that the description does not close.

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 templateId parameter. 'By id' merely restates the parameter name and does not explain the ID format, its origin, or how it relates to other template operations. This is insufficient for a low-coverage schema.

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

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

The description states a specific operation ('Get a single template by id') on a clear resourceressing. The phrase 'including Meta approval status' adds a distinctive detail that separates it from generic listing tools and other getters. It is unambiguous and immediately tells an agent what this tool does.

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?

'Get a single template by id' clearly establishes that this tool is for retrieving one specific template when the caller has a templateId. It does not explicitly name alternatives like list_templates or get_template_variables, but the singular 'by id' condition makes the intended use clear.

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 disclosing behavior. It only states the purpose (getting dynamic variables) but does not mention that this is a read-only operation, whether it requires any permissions, or what the response format looks like. No behavioral traits are disclosed beyond the action itself.

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 sentence with no superfluous words, making it concise and front-loaded. It is appropriately sized for the simplicity of the tool, though the brevity limits its informativeness.

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 (one parameter, no output schema), the minimal description is barely adequate. However, it omits any details about the return value structure, whether the template must already exist, or any preconditions. For an agent to call it correctly, more context would be helpful, especially given the large sibling toolset.

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 input schema has 0% description coverage, and the description does not explain the 'templateId' parameter at all. The tool name and description do not hint at what kind of identifier is expected (e.g., a GUID, a numeric ID) or how it relates to templates. The description adds no value beyond the schema definition.

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 verb 'Get' and the resource 'dynamic variables of a template', making the tool's purpose transparent. However, it does not explicitly differentiate from sibling tools like gambot_get_template, relying on the tool name rather than description to set it apart.

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 whether it should be called before sending a template to obtain required variables, or if it overlaps with gambot_get_template. The description provides no context or exclusions.

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 burden of behavioral disclosure. 'Get' and 'single...by id' convey a read-only, one-record lookup, but the description does not mention possible 404 behavior, required authorization, or the shape of the returned user. This is acceptable for a simple getter but not richly transparent.

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, front-loaded sentence: 'Get a single user by id.' Every word adds relevant information and there is no filler or repetition.

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 get-by-id tool with one parameter, the description is close to adequate. However, there is no output schema and no mention of what the response contains or what happens when the user does not exist, so the contextual picture is not fully complete.

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 no parameter descriptions, but the description clarifies that the sole parameter, userId, is the id of the user to retrieve. This adds some meaning beyond the bare schema, yet it does not explain id format or any constraints, leaving the parameter semantics minimally viable.

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: 'Get a single user by id.' The word 'single' distinguishes it from list-style tools like gambot_list_users, and it is clearly scoped to the user resource rather than the many other get_* siblings.

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

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

The description implies when to use it: when a single user is needed by id. However, it does not explicitly mention alternatives like gambot_list_users for fetching multiple users or gambot_get_contact for non-user lookups, so the usage guidance is merely implied rather than stated.

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

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

No annotations are provided, so the description must carry the behavioral burden. It states that the tool returns a hosted page URL, which is useful, but it doesn't mention whether any side effects occur, whether prior WABA configuration is needed, or what error cases may arise. 'Get' implies read-only, but this is not made explicit.

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 one focused sentence that front-loads the core action and return value. The parenthetical clarification about the Facebook popup is useful and not redundant. Every word earns its place.

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

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

The description explains the return value (hosted page URL) and purpose, which is good for a simple one-parameter tool with no output schema. However, it leaves the organization parameter ambiguous and doesn't connect to the related sibling tool gambot_exchange_waba_token, so the full calling context is incomplete.

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

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

The schema has one required parameter, 'organization', with no schema description and 0% coverage. The tool description never mentions the parameter, so it doesn't clarify whether organization is an ID, name, or slug. The parameter name provides some basic meaning, but 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 uses a specific verb ('Get') and identifies the exact resource: the hosted page URL for Meta Embedded Signup. It clearly distinguishes this from other Gambot tools by naming the Facebook popup flow and the WABA connection purpose.

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 gives clear context for when to use the tool: when a customer needs to complete Meta Embedded Signup to connect their WhatsApp Business account. It doesn't name alternatives or exclusions, but the scenario is specific enough to guide selection.

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 behavioral burden. It usefully discloses that the operation locks the invoice and assigns an official number, implying irreversibility. However, it does not mention error conditions, permissions, or what happens if the invoice is already issued.

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 one tight sentence with no filler. The core action is front-loaded, and the distinguishing effect follows immediately in the em-dash clause.

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 one-parameter tool with no output schema, the description covers the essential action and its main side effect. Still, it lacks a note about required prior state or irreversibility, which would make it fully complete for an agent deciding to call it.

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 should compensate. It does not explicitly explain that invoiceId is the identifier of the invoice to lock and number, though the singular parameter name makes this partially inferable.

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 action ('Issue an invoice') and clarifies the key effect: 'locks it and assigns the official document number.' This distinguishes it from create/update/list/get invoice siblings, though it never names an alternative explicitly.

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

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

The description gives no guidance on when to use this tool versus create_invoice, update_invoice, or other invoice tools. It implies finalization via 'locks it' but never states prerequisites, such as the invoice being a draft or not already issued.

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 only says 'List all broadcast campaigns' and does not disclose whether this is read-only, whether it returns paginated results, what fields are included, or whether it includes scheduled/draft campaigns. The word 'broadcast' adds some scope but not behavioral detail.

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?

One sentence, no filler, and the key scope ('broadcast campaigns') is front-loaded. Every word earns its place.

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

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

For a zero-parameter list tool, the description is minimally adequate: it names the resource and scope. However, with no output schema and no annotations, it would benefit from stating whether the result is a list of campaign IDs/names and whether any filtering or pagination applies. The sibling list shows many campaign-related tools, so a bit more differentiation would improve completeness.

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

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

The tool has zero parameters, so there is no parameter semantics burden. The description's mention of 'broadcast campaigns' clarifies the resource scope, which is the only semantic context needed. Baseline 4 for zero params is appropriate.

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 ('List') and resource ('broadcast campaigns') and scopes it to the organization. It is clear enough to distinguish from related tools like gambot_list_scheduled_campaigns and gambot_get_campaign, though it does not explicitly name those siblings.

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

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

The description implies usage: call this when you need all broadcast campaigns for the organization. It does not explicitly state when to prefer this over gambot_list_scheduled_campaigns or gambot_get_campaign, nor does it mention any exclusions or alternatives.

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

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

With no annotations, the description must carry the full behavioral burden. It only discloses that results are paginated; it does not mention ordering, defaults, what search filters against, or whether this is a read-only operation.

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 three words and every word earns its place. It is front-loaded and contains no filler or repetition.

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

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

The description is too sparse for a tool with three parameters and no output schema. It omits pagination defaults, the semantics of the search parameter, and any indication of what the response contains.

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 to any parameter. 'search' remains ambiguous, and pageSize/pageNumber are only self-explanatory by their names, not by the description.

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 ('List') and resource ('cases'), making the core action clear. It also notes pagination, which distinguishes it from the singular gambot_get_case, though it does not explicitly contrast with any sibling.

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 no explicit guidance on when to use this tool versus alternatives like gambot_get_case or gambot_list_leads. Usage context is only implied by the name and title, not actually stated.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It provides one behavioral detail: conversations are ordered by most recent message. However, it does not disclose pagination defaults, search behavior, return shape, or any side effects. For a list operation, this is thinner than the safety-critical information the tool.

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, front-loaded sentence with no filler, which makes it concise and easy to parse. It does not devote space to unnecessary explanations. However, the conciseness crosses into under-specification—the sentence is too short to cover the tool's important parameter and behavioral details.

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 has 3 parameters, no output schema, and no annotations, so the description must provide all usage context. It does not explain return values, the search filter's behavior, pagination defaults, or any execution context. An agent cannot build a correct invocation from this description and the bare schema alone.

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?

All three parameters (search, pageSize, pageNumber) have zero schema descriptions, and the tool description mentions none of them. The description adds no meaning beyond the parameter names in the schema, and since schema_description_coverage is 0%, this is a critical gap—the agent has no way to understand what 'search' filters, default page size, or how pagination works.

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 action (list), resource (conversations), and even clarifies that conversations are contacts. It also specifies ordering by most recent message, which helps differentiate it from the broad set of sibling list tools. However, it doesn't explicitly distinguish itself from related tools like gambot_get_conversation_messages by name, so the differentiation is implicit.

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 is given about when to use this tool versus alternatives, when to use the search parameter, or how pagination should be handled. The description simply states what it does, leaving the agent to infer the appropriate use context from the tool name. Many siblings exist, but none are referenced as alternatives.

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

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

With no annotations at all, the description carries full responsibility for behavioral disclosure. It merely states the action without revealing what the tool returns (e.g., list structure, pagination), whether it is read-only, or any limits beyond the schema's maximum. The lack of any behavioral detail leaves a significant gap.

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

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

The description is extremely concise, consisting of a single sentence with no wasted words. However, it is under-specifying rather than appropriately concise; it lacks necessary context for effective tool selection. Conciseness is achieved at the expense of informativeness.

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 listing tool with one optional parameter and no output schema, the description does not provide enough context for an agent to know what to expect. It does not mention the response format, whether results are paginated, or how to interpret the limit parameter. Given the presence of similar sibling tools, more differentiation is needed.

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% because the description does not mention the 'limit' parameter. The schema defines it as an integer with a maximum of 1000, but the description adds no meaning about how it affects results (e.g., pagination, default behavior). Since coverage is low, the description should compensate but does not.

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 verb and resource: 'List document templates.' It is specific enough to indicate the action, but it does not differentiate from the sibling tool gambot_list_templates, which may refer to a different type of template (e.g., WhatsApp message templates). The purpose is clear but lacks distinction.

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 is provided on when to use this tool versus alternatives like gambot_list_templates or gambot_get_document. The agent must infer based on naming, which is not reliable. There are no mentions of exclusions or prerequisites.

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 only states the action and gives no information about pagination, return format, authentication requirements, or whether results are limited. It does not contradict annotations (none exist), but it fails to reveal any behavioral traits beyond the implied read-only nature of 'list'.

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 (three words), but it is under-specified rather than concise. It essentially repeats the title and adds no value. Every sentence should earn its place; this one does not, as it provides no information beyond the tool's name. There is no front-loading of useful details because there are none.

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 (one optional parameter, no output schema, no annotations), the description is incomplete for an agent to correctly invoke it. The agent does not know what a 'web form' is in this context, what the response structure looks like, or how to paginate using the limit parameter. Sibling tools like gambot_get_form and gambot_get_form_submissions further complicate selection, but the description offers no clarifications.

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 one parameter (limit, integer, max 1000) with 0% description coverage. The description does not mention the limit parameter at all, nor does it explain its purpose or effect. Since the schema lacks descriptions, the description must compensate but does not, leaving the agent without any understanding of how to use the limit 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 'List web forms' clearly states a specific verb (list) and resource (web forms), distinguishing it from sibling tools like gambot_get_form (retrieve a single form) and gambot_get_form_submissions (get submissions). It is not a tautology because it names the resource explicitly, though it lacks additional qualifiers such as 'all' or 'available'.

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. It does not mention, for example, that gambot_get_form should be used for a single form, or that gambot_get_form_submissions is for submissions. The description provides no contextual cues for selection among the many list/get siblings.

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 disclosing behavior. It mentions 'paginated', which hints at paging, but does not disclose any other behaviors such as filtering, ordering, default page size, limits, or whether it returns only non-deleted invoices. For a tool with five optional parameters, this is a significant gap.

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

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

The description is a single, concise sentence that gets to the point. It is appropriately sized for the minimal info it conveys, but it is not over-bloated. However, it earns no credit for adding extra structure or front-loading important disclaimers; it's just a bare statement.

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 complexity—five optional parameters, no output schema, and no schema descriptions—the description is woefully incomplete. It omits any mention of the parameters, return format, pagination mechanics, or any filtering capabilities. Compared to sibling list tools, it lacks the context needed to choose and use 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 provides no parameter information whatsoever. The schema lists parameters like 'type', 'search', 'status', 'pageSize', and 'pageNumber', but the description doesn't explain what these do or how to use them. An agent would have no way to correctly fill in these parameters based on the description alone.

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 verb 'List' and the resource 'invoices', which distinguishes it from other invoice-related tools like get_invoice or update_invoice. However, it doesn't explicitly differentiate from other list tools (e.g., list_campaigns), though the resource name alone is sufficient to identify its purpose. It also mentions pagination, which is a specific behavior.

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 get_invoice or list_campaigns. It doesn't state that this is for retrieving multiple invoices, nor does it mention any preconditions, such as needing an organization context. The description implies a listing operation but gives no contextual cues.

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 alone must disclose behavior. It reveals only that results are paginated; it does not state read-only status, default page size/page number, behavior with no arguments, or whether search filters server-side or client-side. This is minimal behavioral disclosure.

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 and front-loaded, with no filler words. However, it is mostly a repetition of the title with only '(paginated)' as new content, and it lacks enough structure to qualify as a genuinely helpful definition.

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 three optional parameters, no output schema, and no annotations, this description is under-specified. It omits search semantics, pagination defaults, result format, and any guidance about large result sets. An agent can issue the call but cannot fully predict or control its behavior.

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

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

Schema description coverage is 0%, and the description does not explain 'search', the meaning of pageSize/pageNumber, or pagination defaults. The parenthetical 'paginated' hints at the pagination parameters but adds no semantic detail beyond what the schema already shows.

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

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

The description uses a specific verb and resource ('List leads') and adds the key qualifier 'paginated'. Among the many sibling list_* tools, the resource name clearly differentiates this operation. However, it doesn't describe the lead scope, filters, or return shape, so it falls short of a full 5.

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 vs alternatives, no exclusions, and no mention of complementary tools like gambot_get_lead or gambot_create_lead. With dozens of sibling list tools, an agent gets no routing help beyond the resource 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'List orders' and mentions filters; it does not disclose whether the operation is read-only (though listing implies it), whether results are paginated, what the response shape is, or any side effects. This is a minimal description that leaves the agent guessing about 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 a single, compact sentence that front-loads the core action and lists filters in parentheses. It is appropriately sized for a simple list operation, though it could add a bit more behavioral context without becoming bloated.

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 list tool with no annotations, no output schema, and 0% schema description coverage, the description is too thin. An agent needs to know whether results are paginated, what the response format is, and what valid status values are. The sibling list tools (e.g., gambot_list_campaigns, gambot_list_leads) suggest a pattern, but the description itself does not provide enough 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?

Schema description coverage is 0%, so the description must compensate for the four parameters. It mentions 'status / store / date range' which covers status, storeId, and dateFrom/dateTo conceptually, but it does not explain the expected format for dates, whether status values are enumerated, or whether storeId is an ID string. The description adds some meaning but leaves significant gaps.

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 ('List') and resource ('orders'), and mentions optional filters (status, store, date range) that map to the parameters. It is distinguishable from siblings like gambot_get_order (singular) and gambot_create_order, though it doesn't explicitly name them.

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 this is the tool for retrieving multiple orders, and the optional filters suggest when to use them. However, it provides no explicit guidance on when to prefer this over gambot_get_order or other list tools, and no context about pagination or result limits.

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 reveals only that the result is paginated, which is a minor behavioral trait. It does not disclose return format, authentication requirements, side effects, ordering, or any constraints beyond pagination. For a list operation with no annotation coverage, this is insufficient.

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, front-loaded sentence with no filler words. It is appropriately concise for a simple list operation, though it borders on under-specification. For a tool with only a name and title, it conveys the core purpose efficiently.

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 no output schema, no annotations, and four optional parameters with no descriptions, the description is far from complete. It does not explain the response structure (beyond pagination), how filters work, or any constraints like the pageSize maximum (even though the schema includes max: 200). An agent would not have enough context to call this tool correctly without additional inference.

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, and the description does not mention any of the four parameters (search, status, pageSize, pageNumber). It fails to explain what these parameters mean or how they affect results. Since the description provides no semantic value beyond the parameter names, it does not compensate for the lack of schema descriptions.

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 action ('List') and the resource ('price quotes'), and adds the pagination detail. It is specific enough to distinguish from other list tools in the sibling set like list_leads or list_cases, though it does not explicitly contrast with get_quote. The verb and object are clear and not a tautology.

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 is provided on when to use this tool versus alternatives (e.g., get_quote for a single quote, or list_invoices for a different resource). There is no mention of scenarios where this tool is appropriate or when another should be chosen. The description offers no context on filtering or typical use cases.

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. The verb 'List' implies a read-only operation and 'waiting to run' clarifies the campaign state, but the description does not mention response shape, pagination, or other behaviors. This is minimally adequate for a simple no-parameter list operation.

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, front-loaded sentence with no filler. Every word adds meaning by identifying the operation, the resource, and the relevant state.

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

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

For a zero-parameter list operation, the description is nearly complete: an agent knows what to expect and how to invoke it. The main gap is the lack of differentiation from gambot_list_campaigns and the absence of any return-format hints, but the tool's low complexity reduces the impact of these omissions.

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 input schema has zero properties, so there are no parameters to document. The baseline for a no-parameter tool is 4, and the description's 'scheduled campaigns waiting to run' effectively defines the implicit selection criteria.

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

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

The description uses the specific verb 'List' and identifies a precise resource: scheduled campaigns that are waiting to run. It clearly distinguishes this from the sibling gambot_list_campaigns by narrowing to the scheduled/waiting state.

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 gives no guidance on when to use this tool instead of gambot_list_campaigns or other campaign-related tools. It does not state any exclusions, prerequisites, or alternative conditions, leaving the choice 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 burden. 'List' implies a non-destructive read and 'newest first' discloses ordering, but the description does not mention pagination, response shape, or any side effects/authorization 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?

One short sentence with the key action and ordering front-loaded; no filler.

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

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

For a simple one-parameter list tool, the description is minimally viable: it names the resource and order. It is incomplete because it does not clarify the default/meaning of limit, pagination, or how this relates to the sibling document/signature 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?

The schema describes only 'limit' with a maximum of 1000 and no textual description, and the tool description does not mention it. The parameter is fairly self-explanatory and constrained, but the description adds no semantic value for it.

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

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

The description uses a specific verb ('List') and a specific resource ('e-signature documents'), and adds a sort order ('newest first'), so an agent knows what the tool returns. It does not distinguish itself from the sibling gambot_list_documents, so it misses the top level of differentiation.

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 statement of when to use this tool versus gambot_list_documents, gambot_get_signature, or gambot_get_signature_link. The ordering hint implies a listing use case, but no explicit when/when-not guidance is present.

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 must carry behavioral disclosure, but it only says 'List tasks'. It does not mention result format, pagination, whether all tasks are returned, or whether the operation is a safe read; this is a meaningful gap for a listing operation.

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 entire description is a single sentence with no filler; the verb and resource are front-loaded. It is concise, though it sacrifices behavioral context for brevity.

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

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

For a zero-parameter list operation, 'List tasks for the organization' is a minimum viable description: there are no inputs to specify. However, without an output schema or annotations, it does not state what the returned task data looks like or any list limits, leaving moderate gaps.

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

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

The tool has zero parameters and an empty input schema, so there is no parameter semantics for the description to clarify. Per the 0-parameter baseline, the lack of parameter details is acceptable and non-penalizing.

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 action ('List') and resource ('tasks') with an organizational scope, which makes the basic purpose clear. It is distinguishable from sibling list tools because the resource is explicit. It does not, however, elaborate on whether this includes all task states or only active tasks.

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 no guidance on when to choose list_tasks over alternatives like get_task, list_leads, or list_campaigns. There are no stated exclusions or conditions, so an agent must infer usage solely 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'List' clearly indicates a read-only operation)Skip plausible destructive behavior, and 'all' signals broad scope. Yet it does not disclose potential pagination, output shape, authentication requirements, or any rate limits, though these are minor for such a simple operation.

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?

ExampleSingle sentence with no wasted words. The key components (verb, resource, scope) are front-loaded and clearly presented. Every part earns its place.

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