KaiCalls

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

Annotations provide readOnlyHint=false, destructiveHint=false, and idempotentHint=true, which are consistent with the description. The description adds no behavioral details beyond the annotation hints, such as error behavior if the number is already assigned or idempotency guarantees. With annotations already covering the safety profile, the description adds minimal additional transparency.

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 sentences, each earned: first states the core action and optional routing, second clarifies what it does not do and directs to an alternative, third references the underlying API. No wasted words, front-loaded with the most important information.

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

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

The tool has an output schema (indicated by context), so return value explanation is not needed. All three parameters are documented in the schema, and the description covers purpose, usage guidance, and behavioral caveats. The tool is relatively simple, and the description is fully adequate for 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 100%, but the description adds value by explaining that phone_number must be 'already in the registry' and that business_id is optional only when the token can access exactly one business. This context goes beyond the schema's descriptions, which only specify type and requirement.

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 'Assign' and the resource 'phone number already in the KaiCalls registry pool'. It explicitly distinguishes from purchasing a new number by directing to search_available_numbers + buy_number, which differentiates it from sibling tool buy_number.

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

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

The description provides explicit guidance on when not to use this tool ('Does NOT purchase a new number — use search_available_numbers + buy_number for that'), giving clear context for alternatives. It also mentions the optional routing to an agent, but does not explicitly contrast with detach_number or other sibling tools.

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

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

Annotations already mark destructiveHint=true and idempotentHint=false. Description adds value by stating billing is immediate and that agent attachment is separate. Also mentions compliance handling. No contradictions.

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?

Three sentences, front-loaded with core action and key constraints. No wasted words. Every sentence adds value.

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?

Covers billing, agent attachment, compliance, and API mapping. Missing details like refund policy or cancellation, but sufficient for a purchase tool with existing output schema.

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

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

Schema coverage is 100%. Description adds context: phone_number must be E.164 from search_available_numbers, agent_id is optional and suggests follow-up, business_id optional only with single-business token. Enhances understanding beyond 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?

Clearly states 'Purchase a real phone number' with verb+resource. Distinguishes from sibling tools like search_available_numbers (search vs buy) and attach_number (attach vs buy).

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 notes that it spends real money and does not auto-attach an agent, advising a follow-up attach_number call. Provides API route and compliance info. Lacks explicit when-to-use vs alternatives but context is sufficient.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds no extra behavioral context beyond what the annotations provide, which is adequate but not improved upon.

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, front-loaded sentence with no unnecessary words. It efficiently conveys the essential information.

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

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

For a simple, single-parameter tool with annotations and an output schema, the description is functionally complete. However, it could briefly mention what status values might be returned or any caching behavior for better 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 input schema has 100% coverage for its single parameter, and the description merely restates 'by its ID' without adding format, validation, or additional context. Baseline 3 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 'Check the status of a call by its ID' clearly states the action (check), resource (call), and key parameter (ID), and it distinguishes from sibling tools like get_business_info or get_transcript by focusing specifically on status.

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. The description does not mention context, prerequisites, or scenarios where other tools would be preferred, leaving the agent without usage 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?

The description adds context beyond annotations: it mentions 'safely' and 'governed agent.patch broker', indicating a write operation with governance. This complements the annotations (destructiveHint=true, idempotentHint=true) by explaining the safety and routing mechanism. No contradiction; the description aligns with the annotations while adding valuable behavioral context.

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

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

The description is two sentences: the first states the core operation, the second lists use cases. It is front-loaded and every sentence earns its place. No unnecessary words or repetitions. Highly concise.

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 (11 parameters, nested objects, output schema), the description covers the essential purpose and common use cases. It does not describe the output or the broker details, but the presence of an output schema means that responsibility can be delegated. The description is sufficient for an agent to decide whether to invoke this tool, though it could briefly mention that parameter details are in the schema.

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

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

The input schema has 100% description coverage, so the baseline is 3. The description does not elaborate on individual parameters; it focuses on the tool's purpose. While it references 'named operational rules section' (corresponding to section_title) and 'cross-business handoffs' (sample rules), it adds minimal parameter-level 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?

The description clearly states the tool's function: 'safely add or replace a named operational rules section inside an agent inbound prompt'. It specifies the resource (agent inbound prompt), the action (add/replace a section), and the mechanism (routed through governed broker). The use cases (cross-business handoffs, callback language, alert promises, client-specific rules) further distinguish it from siblings like configure_staff_alerts or configure_textable_links.

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 provides usage scenarios: 'cross-business handoffs, callback language, alert promises, and client-specific operating rules'. It implies when to use this tool (for operational rules in agent prompts) but does not explicitly state when not to use it or compare with siblings like request_kaicalls_update. The guidance is clear but lacks exclusionary 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?

Annotations indicate destructiveHint=true and idempotentHint=true. Description mentions 'Configure' and includes dry_run parameter, suggesting writes, but does not warn that existing settings may be overwritten.

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 core purpose, no wasted words. Lists use cases succinctly.

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?

Output schema exists, so return values are covered. Description provides sufficient context for when to use the tool, though dry_run and destructive behavior could be explicitly noted.

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 covers 100% of parameters with detailed descriptions. The tool description adds minimal extra meaning beyond the schema, which is acceptable for high coverage.

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 clearly states it configures staff alert recipients and escalation rules, with specific use cases (emergency texts, callback alerts). Differentiates from siblings like configure_agent_business_rules and configure_textable_links.

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?

Describes when to use (emergency/urgent texts, callback alerts, etc.) but does not explicitly mention when not to use or alternatives among 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?

Annotations indicate destructiveHint=true and idempotentHint=true. The description adds behavioral context: it can create or repair entries, rejects kaicalls.com destinations, and explains dry_run behavior. No contradictions; it enriches the annotation signals with specific constraints.

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 primary action. No fluff or redundancy. Every part serves a purpose: action + resource, then usage context. Efficient and clear.

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

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

Given the tool has an output schema (not shown) and full parameter coverage, the description adequately covers purpose, usage, and key constraints. It lacks error or rate limit details, but these are less critical with annotations and output schema present. Overall complete for its 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 100%, so baseline is 3. The tool description repeats some parameter info (e.g., 'New links require label and destination_url') but does not add new meaning beyond the schema. It provides a high-level summary but no extra detail.

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 creates or repairs business_links entries for the send_link/send_sms tools, with specific action (Create/repair) and resource (business_links). It distinguishes from sibling tools (e.g., not calls, agents, analytics) and includes example use cases (booking, directions, cancellation).

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 advises when to use ('Use this when callers need ... links texted without exposing raw URLs'). It implies not to use for other purposes, but does not list alternatives or explicit when-not-to-use. The sibling list provides context, so guidance is clear but not exhaustive.

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

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

The description adds significant behavioral context beyond annotations: it explains that mutations are versioned ('assistant_config_versions'), reversible via rollback_config, and that compliance auto-applies AI-disclosure and consent handling. Annotations only indicate readOnlyHint=false and destructiveHint=false, so the description enriches understanding of side effects and safety.

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 four sentences with no wasted words. The primary action is front-loaded, and additional behavioral details are added without redundancy. Every sentence adds value.

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 8 parameters, nested objects, a rich output schema, and many sibling tools, the description covers creation behavior, versioning, rollback, and compliance. It does not mention prerequisites (e.g., business_id must exist) or typical workflows, but the schema handles parameters. The output schema is mentioned as existing, so return values are covered.

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 100%, so the input schema already describes all 8 parameters. The description adds high-level context (e.g., 'system prompt, greeting, voice, and model') but does not provide additional meaning or constraints beyond what the schema already captures. Baseline 3 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 clearly states the verb ('Create'), the resource ('a new KaiCalls voice agent'), and the key components ('system prompt, greeting, voice, and model'). It distinguishes from sibling tools like 'configure_agent_business_rules' by focusing on initial creation rather than configuration.

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 context about versioning and reversibility, and mentions compliance, but does not explicitly state when to use this tool over alternatives (e.g., update_agent_config) or when not to use it. No direct comparison to siblings is given.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, consistent with creating a campaign. The description adds valuable context: TCPA/consent gating still applies at dial time and admin role requirement. It does not contradict annotations and provides beyond what annotations convey.

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?

Three sentences, front-loaded with the primary action. No wasted words, though the description could be slightly more concise by combining some clauses. Still well-structured and efficient.

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 (7 params, nested objects) and presence of an output schema, the description adequately covers creation, launch behavior, consent constraints, and role requirement. It is sufficient for an agent to understand the tool's purpose and key considerations, though it omits the agent_id constraint when launch is true (only in schema).

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

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

Schema coverage is 100%, so the schema already documents all 7 parameters with descriptions. The description adds high-level context (e.g., 'optionally launch it immediately', 'cadence_config' structure) but does not significantly enhance individual parameter understanding beyond the schema. Baseline 3 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 clearly states 'Create an outbound call campaign' with a specific verb and resource. It distinguishes from siblings like 'list_campaigns' or 'upsert_lead' by focusing on campaign creation, but could be more explicit about alternatives.

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

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

The description specifies an admin role requirement but does not provide guidance on when to use this tool versus alternatives (e.g., when to launch vs. create without launch, or when to use other tools like 'configure_agent_business_rules'). No explicit when-not-to-use or alternative tool mentions.

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

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

Annotations already provide key behavioral traits (destructive, idempotent). The description adds the REST API mirror ('Mirrors DELETE /api/v1/webhooks'), which gives extra context. No contradictions. Does not detail other effects but sufficiently complements annotations.

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 no unnecessary words. Front-loaded with the action and resource. 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?

With annotations covering safety and idempotency, and an output schema existing, the description is adequate. It specifies the action and provides REST context. Could mention return values or prerequisites, but overall complete for a simple delete tool.

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?

Input schema covers all parameters with 100% description coverage. The description mentions 'by ID' reinforcing the id parameter but adds no new semantics beyond what the schema provides. Baseline of 3 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 clearly states the verb 'Remove', the resource 'business outbound webhook', and the method 'by ID'. It also mentions the corresponding REST endpoint, distinguishing it from sibling tools like set_webhook and get_webhook.

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 does not explicitly state when to use this tool or provide alternatives. It implies usage for deleting a webhook but lacks guidance on context or when not to use it. The idempotentHint in annotations hints at safe retry, but the description itself offers no usage 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?

Annotations already indicate destructiveHint=true and idempotentHint=true. The description confirms the destructive nature ('release', 'mirrors DELETE') but adds minimal extra context beyond what annotations provide.

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 efficient sentences with no wasted words. The action and key detail (mirroring DELETE) are 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 simple destructive operation, the description covers the essential information. It could mention the existence of the reverse operation (attach_number) or any irreversible consequences, but the presence of output schema and annotations compensates.

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 100% with descriptions for both parameters. The description does not add additional meaning beyond the schema; it simply mentions the phone_number parameter inline.

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 (release), resource (phone number), and destination (unassigned registry pool). It also mentions the mirrored API endpoint (DELETE), distinguishing it from siblings like attach_number and buy_number.

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

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

No explicit guidance on when to use this tool versus alternatives. While the purpose is clear, there is no mention of when not to use it or how it relates to attach_number (reverse operation).

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint as safe. The description adds that it returns a 'dashboard summary' over a 'recent time window,' which is consistent but does not disclose additional behavioral traits beyond what annotations provide.

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?

Single sentence efficiently lists the key metrics and scope. No unnecessary words; structured to front-load the purpose ('dashboard summary').

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 presence of an output schema (not shown), the description sufficiently covers what the tool returns. The single parameter is clear. Minor gap: could explicitly state that data is aggregated and not individual records.

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 100% with one parameter 'days' described in the schema. The description mentions 'recent time window' but does not explicitly link to the parameter or provide additional meaning beyond the schema definition. Baseline 3 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?

Description clearly identifies the tool as returning a dashboard summary with specific metrics (lead counts, conversion rate, etc.), which distinguishes it from data retrieval tools. However, it does not explicitly differentiate from siblings like get_business_info or list_recent_calls.

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 for high-level metrics over a time window but does not state when to use this tool instead of alternatives or provide exclusion criteria. Adding context like 'for overall trends, not detailed records' would improve clarity.

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

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

Annotations already declare readOnlyHint and idempotentHint. The description adds value by specifying the scope (across every business the caller can access) and the exact data returned (minutes-used and subscription status per business). It does not contradict annotations.

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-loaded with the core purpose, followed by a technical reference. 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?

Given the absence of parameters and presence of annotations and output schema, the description is fairly complete. It explains the output and scope, though it could mention that authentication is implicitly required. Still, it covers the essential 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?

With zero parameters and 100% schema description coverage, the description does not need to add parameter details. The baseline of 4 is appropriate as the description does not introduce any confusion.

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 specific resource 'per-business minutes-used and subscription status across every business the caller can access.' It is precise about what data is returned and the scope, differentiating it from sibling tools like get_usage or get_analytics.

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 on when to use this tool versus alternatives. While it mentions 'Mirrors GET /api/v1/balance,' it does not provide context for when to prefer this over other read tools, such as get_usage, nor does it state any prerequisites 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it returns agent count and call stats, but does not disclose other behavioral traits like authentication requirements or rate limits.

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

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

The description is a single concise sentence that gets straight to the point. 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?

Given a single optional parameter and an output schema (which removes need to explain return format), the description adequately describes what the tool returns. However, it could briefly mention what 'business information' includes for 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 input schema has 100% coverage with a clear description for the single optional parameter. The description does not add any extra meaning beyond what the schema already provides, so baseline 3 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 clearly states the tool retrieves business information, agent count, and recent call stats. This distinguishes it from siblings like list_agents (only agents) and list_recent_calls (only calls).

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 use when aggregated business data is needed, but lacks explicit guidance on when to use this tool versus alternatives or when not to use it.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context about the tool's purpose (listening to audio) but does not disclose additional behavioral traits like auth requirements, error handling, or rate limits. With annotations covering safety, the description adds marginal value.

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

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

The description is a single 20-word sentence that front-loads the purpose and key differentiator. Every word adds value; no repetition or fluff.

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

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

The description covers the core functionality for a simple tool with one parameter and an output schema. However, it omits edge cases (e.g., recording not found) that could be helpful for an agent. Minor gap given the simplicity.

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 100%, so the schema fully describes the 'call_id' parameter. The description does not add extra semantics or constraints beyond what the schema provides, thus baseline score of 3 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 clearly states the verb 'get' and the resource 'real call recording URL', and explicitly contrasts with the sibling 'get_transcript' by mentioning 'instead of relying only on the transcript'. This makes the purpose specific and distinct.

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 (need audio) and when not (transcript sufficient) by saying 'so reviewers can listen… instead of relying only on the transcript'. It does not explicitly name alternatives, but the sibling 'get_transcript' is implied.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description confirms this by describing it as an audit trail. It adds context that mutations are logged and reversible, which goes beyond annotations and gives confidence 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 two sentences, front-loaded with the main purpose and output fields. Every sentence adds value, with no redundant information. It is efficiently 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 that an output schema exists, the description does not need to detail return values. It covers the source (admin_change_history), relationship to the voice tool, and the scope of logged mutations, making it complete for a list tool.

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 100%, so parameters (agent_id, limit) are fully defined in the schema. The description does not add additional semantic details beyond the schema, but it does not need to. Baseline 3 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 clearly states the tool lists an agent's config-change audit trail with specific fields (change_type, change_source, old/new value, timestamp). It distinguishes itself from siblings by focusing on change history, which no other sibling tool does. The verb 'list' and resource 'change history' are precise.

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 explains that every mutation by KaiCalls is logged here and reversible, implying it is the tool to inspect changes. However, it does not explicitly state when not to use it or mention specific alternatives, though the context is clear enough for an agent.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds no additional behavioral context beyond 'Get', which is consistent. No contradictions.

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 action and endpoint mirror, no wasted words. Perfectly concise.

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 1-parameter read operation with existing output schema, the description covers all necessary context: what it does, the key parameter, and endpoint reference.

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 100% for the single parameter, and the description repeats the schema's intent ('by ID') without adding extra meaning, such as format requirements or examples.

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

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

The description explicitly states the tool gets a single SMS conversation by ID, clearly distinguishing it from sibling tools like list_conversations which would return multiple. The verb 'Get' and resource 'SMS conversation thread' are specific.

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 does not provide explicit guidance on when to use this tool vs alternatives, though it implies use when you have a specific conversation ID. No when-not-to-use or alternative suggestions are given.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context about returning full details and the AI lead score, which is consistent and provides additional insight beyond annotations.

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?

Single sentence with 18 words, front-loaded with the main action. No fluff; every word earns its place. Excellent structure 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?

Given the presence of an output schema (not shown but noted), the description completes the picture by highlighting the inclusion of the AI lead score. For a single lead fetch tool, this is comprehensive and sufficient.

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 lead_id, so baseline is 3. The description does not add extra meaning beyond what the schema provides ('The lead ID to fetch'). Acceptable but not enhanced.

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 clearly states the verb (get), resource (single lead by ID), and distinguishes from siblings like list_leads. It specifies the inclusion of 'latest AI lead score and explanation', which adds unique value.

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?

While no explicit when-not-to-use or alternatives are given, the description implies usage when you need full details for a specific lead. The context of having a lead ID is clear, and the sibling list_leads suggests an alternative for multiple leads.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds no new behavioral traits beyond confirming the audit nature. It does not contradict annotations.

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 covering purpose and scope, front-loaded with the main action. Slightly dense but efficient with 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?

Covers what the tool retrieves with a detailed list. Output schema exists, so return values need no explanation. Complete enough for a read-only audit tool.

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 100% with the business_id parameter fully explained in the schema. The description adds no additional parameter guidance, so baseline 3 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 uses the verb 'audit' and specifies the resource 'business-level operational setup,' listing exact components like staff alert recipients and escalation rules. This clearly distinguishes it from sibling tools like configure_staff_alerts or get_business_info.

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 it is needed 'before changing a client account,' providing clear context. However, it does not explicitly exclude alternatives or list when not to use, which is a minor gap.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds only that the tool gets transcript and summary of a completed call, contributing minimal behavioral context beyond what annotations provide.

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 of 9 words with no unnecessary information. Every part 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?

Given the tool has a simple single parameter, comprehensive annotations, and an output schema, the description sufficiently covers the purpose and key condition (completed call). No critical gaps remain.

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 100% with a single parameter 'call_id' already documented. The description's mention of 'completed call' adds context but does not meaningfully extend parameter semantics 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 clearly states the tool retrieves both transcript and summary of a completed call, using the verb 'get' and specifying the resource. It distinguishes from siblings like check_call_status or list_recent_calls, which serve different purposes.

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

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

The description mentions 'completed call', implying the call must be finished, but does not explicitly state when to use this tool versus alternatives like check_call_status to verify completion first. No exclusions or alternative tool references 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds that it returns recent usage events with specific fields (endpoint, method, status code, cost) and mirrors a known API endpoint, providing useful behavioral context beyond annotations.

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 no redundancy. Each sentence adds value: first states purpose and output fields, second notes API mirroring. No fluff.

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

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

Tool has output schema (not shown) and 3 optional parameters with solid schema coverage. Description explains what events include and that it's for the caller's account, which is sufficient. Minor gap: no mention of time range or pagination behavior, but parameters cover bounds and limit.

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 100% with each parameter documented. Description does not add any new parameter-level information beyond what is already in the schema, so baseline score of 3 applies.

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

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

Clear verb 'List', specific resource 'API usage events' (endpoint, method, status code, cost), and scope 'for the caller's account'. Distinguishes from siblings like get_analytics or list_recent_calls by focusing on usage events.

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 on when to use vs alternatives (e.g., get_analytics for broader metrics). Only mentions mirroring a specific API endpoint, which implies context but lacks exclusions or scenarios.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description does not need to repeat these. It adds no further behavioral context beyond the schema. No contradiction.

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

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

Two short sentences, front-loaded with the verb 'list', no extraneous information. Every word is necessary.

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

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

For a simple read-only tool with one optional parameter, an output schema exists (not shown but noted), and the description covers the purpose fully. No gaps given the low 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 100% (the single parameter business_id has a description). The tool description does not add any additional meaning for that parameter. Baseline score of 3 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 clearly states the action (list), resource (webhook(s)), scope (for a business), and included content (supported event types). It distinguishes from sibling tools like set_webhook and delete_webhook.

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. The only extra information is an API endpoint reference, which does not help an agent decide 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?

Annotations already declare read-only and idempotent. Description adds scope (authenticated account) but no other behavioral details like results format or pagination beyond 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?

One concise sentence, no unnecessary words, 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?

Sufficient given annotations and schema. Could optionally mention pagination defaults or that output is array, but output schema handles that.

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

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

Schema provides full parameter descriptions (100% coverage). Description adds no extra meaning to parameters, so baseline 3.

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?

Verb 'List' specifies operation, resource 'KaiCalls agents' is clear, and 'available to authenticated account' adds scope. Distinguishes from siblings which are about calls, transcripts, business info.

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 comparison to siblings. Usage is implied by purpose; no when-not-to-use or alternative guidance. Could mention that this is for browsing agents vs. checking call status.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds the context of 'outbound call campaigns' and 'authenticated business', which is useful but does not disclose additional behavioral traits like pagination or sorting.

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 waste. Every word adds value.

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 presence of an output schema and annotations, the description is sufficient for a simple list tool. It covers the resource and scope, though it could mention pagination explicitly. Still, 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 100%, and the description does not add any meaning beyond what the input schema already provides for limit, offset, and status. Baseline 3 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 clearly states the verb 'list', the resource 'outbound call campaigns', and the scope 'for the authenticated business'. It is specific and distinguishes from sibling tools like list_agents or list_leads.

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 does not provide when or when not to use this tool, nor does it mention alternatives. Usage is implied from the name and resource, but no explicit guidance is given for filtering by status or pagination.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral details: the output is 'hashed, redacted' and includes 'rollback lineage'. This goes beyond annotations without contradiction.

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

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

The description is extremely concise with two sentences, front-loading the main purpose. Every word adds value with no 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?

Given that an output schema exists and annotations cover safety and idempotency, the description adequately covers the tool's two modes, the nature of the data (hashed/redacted), and the rollback lineage. It provides sufficient context for correct usage.

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

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

Schema description coverage is 100%, so baseline is 3. The description repeats the schema's parameter descriptions verbatim for limit and version, adding no new meaning. It does not mention agent_id 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 clearly states the tool lists agent config version history (hashed, redacted, with rollback lineage) and distinguishes between listing all versions and fetching a single version via the `version` parameter. It is specific and differentiates from any 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 explicitly explains when to use the `version` parameter to fetch a single version versus omitting it to list. While it doesn't provide when-not or alternatives, the context is clear enough for the agent to choose correctly.

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

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

Annotations already indicate readOnly, non-destructive, idempotent. Description adds value by specifying the data type (counterparty timeline metadata) and ordering (most recent first), enhancing beyond annotations.

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, no fluff. First sentence immediately conveys purpose and ordering, second provides API reference. Highly efficient and 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 simple list tool with one optional parameter and an output schema, the description covers the essential aspects (what is listed, ordering). Could mention pagination, but the output schema likely handles return format.

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 100% with the limit parameter fully described in the schema (default 50, max 100). Description adds no further parameter semantics, so baseline score of 3 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?

Clearly states it lists SMS conversation threads for the authenticated business, ordered most recent first. Distinguishes from sibling tools like get_conversation (singular) and list_sms_messages (messages within conversations).

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

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

Provides clear context: for the authenticated business, most recent first. Implicitly differentiates from get_conversation by being a list operation, but lacks explicit when-not-to-use or alternative suggestions.

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

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

Annotations already provide readOnly, idempotent, non-destructive hints. Description adds context about data type (canned mock-conversation) and API mirror, which is helpful but not essential.

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 redundant information. Efficient and 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?

Complete for a simple list tool with one optional parameter and an output schema. No missing information needed for an agent to decide tool 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 100% with agent_id described as optional filter. Description implicitly adds scope context ('for an agent or all'), but does not add new parameter semantics 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?

Description clearly states it lists canned mock-conversation eval scenarios, for a specific agent or all accessible agents. Verb 'list' and resource 'eval scenarios' are precise. Distinct from sibling 'run_eval'.

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?

Implies usage for browsing available evals before running them. Could explicitly mention when not to use or recommend pairing with 'run_eval', but context is clear enough.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds the API mirroring detail but no additional behavioral traits like pagination or 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 sentences with no redundancy; front-loaded with the purpose and a reference to the underlying API.

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

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

For a simple list tool with output schema present, the description is adequate; missing details like pagination or ordering but not critical given the schema.

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

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

Schema description coverage is 100%, so the description adds no extra meaning beyond what the schema already provides for each 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 clearly states the tool lists agent knowledge base entries for a business, distinguishing it from the write sibling upsert_knowledge.

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 on when to use this vs alternatives; usage is implied by the name and the mention of mirroring a GET endpoint, but no when-not-to-use 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by mentioning that the AI lead score is included when available, beyond what annotations provide. However, it does not describe pagination behavior or rate limits.

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

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

Two sentences, each serving a purpose: the first states the main function and filters, the second adds the AI score note. 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?

With a full schema and output schema present, the description provides sufficient context for the main use case. It lacks mention of pagination or empty results, but given the tool's simplicity and annotation coverage, it is fairly 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 100%, so the schema already documents all parameters. The description merely echoes the fact that filters are optional, adding no new semantics 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 clearly states 'List leads for the authenticated business' with specific verb and resource. It mentions optional filters and the inclusion of AI lead score, distinguishing it from sibling tools like get_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?

The description implies when to use this tool (when you need a list of leads) but does not explicitly state when not to use it or contrast with sibling tools. It provides clear context but lacks exclusions or alternative 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds that it returns capability and compliance flags and mirrors an API, which provides some additional context but is not deeply revealing of 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?

Two efficient sentences: the first describes the action and output, the second provides an API reference. No wasted words, though the API reference could be integrated into the first sentence.

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 presence of an output schema and comprehensive annotations, the description covers the essentials. It explains what the tool returns and references the API, making it sufficiently complete for a simple list operation.

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 100% and the parameter description in the schema already explains 'business_id'. The tool description does not add further meaning to parameters beyond the schema, meeting the baseline for high coverage.

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 lists phone numbers with capability and compliance flags, and it references the specific API endpoint. It uses a specific verb 'List' and resource 'phone numbers', leaving no 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?

No guidance on when to use this tool versus alternatives like 'search_available_numbers'. The description does not specify context or exclusions, leaving the agent without decision support.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering safety. The description adds behavioral context: it uses bounded keyset pagination, returns compact and redacted data, and is business-scoped. This provides value beyond annotations.

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, front-loaded with purpose. The second sentence adds essential technical details (API mirror, pagination type) without 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?

Given 17 parameters with high schema coverage and an existing output schema, the description provides adequate context for initial understanding. However, it could clarify terms like 'compact' and 'redacted' to fully describe the behavior. Still, it is complete enough for most use cases.

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 high (82%), so the schema itself explains most parameters. The description adds no new parameter-level information beyond mentioning pagination, which is already documented in the cursor parameter schema. Baseline 3 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 clearly states it lists a business-scoped timeline of two distinct event types (call-runtime and integration-delivery). This differentiates it from sibling tools like list_conversations or list_recent_calls, which focus on different resources.

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 on when to use this tool vs alternatives (e.g., list_recent_calls for call-only events). The technical note about mirroring a REST endpoint and bounded pagination implies some usage context but lacks clear when-to-use or when-not-to-use instructions.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the description's statement 'List' adds no new behavioral insight beyond what the agent can infer from annotations. No additional traits (e.g., pagination, rate limits) are disclosed.

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?

Extremely concise—two short sentences that convey purpose and endpoint reference with no extraneous information. Front-loaded with the core action and resource.

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

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

For a simple read-only list operation with a fully described schema, an output schema present, and clear annotations, the description is complete. No additional details (e.g., pagination or sorting) are necessary for correct agent 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 100%, so the input schema already describes each parameter thoroughly. The description adds no additional semantic value beyond echoing the schema fields. Baseline of 3 is appropriate given the high coverage.

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?

Clearly states the action ('list') and resource ('a business's agent product catalog'), and distinguishes from siblings by specifying 'product catalog' as opposed to other entities like agents or campaigns. The reference to the REST API endpoint adds precision.

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?

Implied usage as a read-only list operation, but no explicit guidance on when to use this tool versus other list tools (e.g., list_agents, list_campaigns) or when not to use it (e.g., for filtering specific fields not covered by parameters).

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

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

Annotations already declare readOnlyHint and destructiveHint, so the safety profile is clear. The description adds minimal context (authenticated business) but does not contradict annotations.

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, but it could be slightly expanded with key 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?

Despite having an output schema and good annotations, the description omits details like default ordering, recency definition, and result format, leaving gaps for a list tool.

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 100% and each parameter has a description; the tool description adds no further meaning beyond what is in 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 clearly states the tool lists recent calls for the authenticated business, but it does not differentiate from sibling tools like check_call_status or get_transcript.

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 such as check_call_status or get_transcript; lacks exclusions or 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the description does not need to repeat safety traits. It adds context about 'recent' messages and filtering, which is helpful but not extensive.

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 long, front-loads purpose, and contains no redundant information. Every word serves a 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 read-only paginated list endpoint with an output schema, the description covers the main functionality and filters. Pagination is implicit via limit/offset in the schema, so no mention needed. Lacks explicit mention of default ordering or scope, but sufficient.

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 100% with descriptions for all 4 parameters. The description mentions the two filters (conversation_id, direction) but does not add significant meaning beyond the schema. Baseline 3 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 clearly states the tool lists SMS messages for the authenticated business, with filtering by conversation or direction. This distinguishes it from sibling tools like list_recent_calls or list_voicemails.

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 specifies when to use the tool (to list SMS messages) and mentions filtering options, but lacks explicit guidance on alternatives or when not to use it. However, the resource is unique enough to imply 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that results include transcripts and recording URLs, which is useful but not essential given the output schema exists. It does not specify the recency window or any caching behavior, so transparency is adequate but not enhanced beyond annotations.

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 that immediately conveys the tool's purpose and key features. Every word contributes to understanding, with 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?

Given the tool's simplicity (2 optional parameters, full annotations, and an output schema), the description provides sufficient context for an AI agent to understand its function. It covers the primary elements but leaves out details about pagination behavior beyond the schema defaults, which is acceptable for a listing endpoint with low 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 100%, meaning the input schema already documents the parameters (limit, offset) with defaults and constraints. The description does not add any semantic meaning to these parameters, so it meets the baseline expectation without adding extra 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 (List), the resource (recent voicemails), and the scope (for the authenticated business, including transcripts and recording URLs). It effectively distinguishes this tool from siblings like list_recent_calls, which handles calls instead of voicemails.

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 list_recent_calls or list_sms_messages. The description assumes the agent will infer the context solely from the tool name and resource type, which is insufficient for optimal 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?

Annotations already declare readOnlyHint=true and idempotentHint=true. Description adds value by stating it is 'credential-free' and returns specific fields, but does not contradict annotations.

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?

Description is one sentence plus a short API reference. It is front-loaded with the main action and output, with 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?

Given the presence of an output schema, the description adequately covers the return fields and purpose. It is complete for a simple read-only list tool.

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?

Input schema covers all 3 parameters with clear descriptions (gender, language, provider). Schema description coverage is 100%, so description adds no extra parameter meaning 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?

Description clearly states the tool lists a curated voice catalog, specifies fields returned (id, display name, accent, language, gender, sample URL), and states its purpose for configuring agent voices. It distinguishes from sibling tools as the only voice-related listing tool.

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

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

Description implies usage for configuring agent voices but lacks explicit guidance on when to use versus alternatives. No when-not conditions or sibling comparisons 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?

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds 'real' and 'via KaiCalls AI agent', but does not disclose additional behavioral traits beyond the annotations.

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

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

Single sentence, 14 words, front-loaded with key action and context. 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?

Description is minimal given 6 parameters and output schema. While annotations and schema cover much, the description misses context like prerequisites (e.g., agent must be active). However, output schema exists so return values are documented.

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

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

Schema description coverage is 100%, so the description does not need to add parameter information. It adds no additional 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?

The description clearly states the action ('Initiate'), resource ('real outbound phone call'), and context ('via KaiCalls AI agent'). It distinguishes from sibling tools like check_call_status or list_recent_calls.

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 on when to use this tool vs alternatives, such as prerequisites or when not to use. The purpose implies usage but lacks explicit when/when-not.

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?

Beyond annotations (destructiveHint=true, idempotentHint=true), the description adds valuable context: idempotency_key requirement, human authority for high-risk changes, and possible return values ('needs_user_input, needs_approval, pending_approval, executed, denied, or unsupported — never an unaudited side effect'). No contradictions with annotations.

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

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

The description is front-loaded with purpose, then usage guidelines, then behavioral details. It is dense but every sentence serves a purpose. Could be slightly shorter, but given the complexity it is appropriate.

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 12 parameters and nested objects, the description covers purpose, usage, behavior, and parameter semantics sufficiently. Output schema exists, so lack of return value description is acceptable. The only minor gap is not detailing the authority object structure, but it's in the schema.

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

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

Schema coverage is 100% with clear descriptions per parameter, so baseline is 3. The description adds value by explaining the payload specifics for each intent (E911 address, transcripts webhook_url, agent.patch fields), which goes beyond the schema's generic description and helps the agent form correct requests.

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 performs 'scoped, governed mutations' with specific intents (phone.emergency_address.set, transcripts.sink.configure, agent.patch), and distinguishes from siblings by listing preferred alternatives. The verb 'request' and resource 'KaiCalls update broker' are specific.

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 when-to-use and when-not-to-use guidance by listing sibling tools like update_agent_config, configure_agent_business_rules, etc. Also specifies requirements for idempotency_key and high-risk changes needing human authority.

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

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

Annotations already declare destructiveHint=true and idempotentHint=false. Description adds valuable details: overwrites live config, not idempotent, records new version on each rollback, never restores secrets. No contradiction with annotations.

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

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

Two well-structured sentences. First sentence succinctly defines the action and scope; second sentence warns about non-idempotency and side effects. 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?

Together with annotations and output schema, the description fully covers the tool's behavior, scope, and side effects. No missing critical details.

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 100%; description adds context by explaining version_id and version_number as targeting assistant_config_versions rows and that one is required. This supplements the schema without redundancy.

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 clearly states the tool rolls back an agent's voice configuration to a prior snapshot, specifying what is restored (greeting, voice, prompt, scalar model params) and what is not (secrets/credentials). It distinguishes from sibling tools like list_config_versions and get_change_history.

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

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

Provides explicit context: to roll back config, discover target via list_config_versions or get_change_history. Does not explicitly state when not to use, but the non-idempotent warning implies cautious usage.

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

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

The description adds context beyond annotations by noting that the tool bills Vapi compute and mirrors a POST endpoint. It does not contradict the annotations (readOnlyHint=false, openWorldHint=true, etc.), and provides useful behavioral clues about 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?

Two sentences that efficiently front-load the core purpose and parameters, then add billing and endpoint context. Every word is necessary and 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 the output schema exists and 100% parameter coverage, the description adequately covers inputs and side effects. It could mention error behavior or mutual exclusivity of parameters, but is mostly 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 description adds value by clarifying the relationship between eval_id and agent_id (single vs. all scenarios), which is not explicit in the schema alone. With 100% schema coverage, the baseline is 3, and the extra context justifies a 4.

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 purpose: running a single eval scenario by ID or all scenarios for an agent. It specifies the verb 'run' and the resource 'eval scenario', distinguishing it from sibling tools like list_evals.

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 indicates when to use the tool (to run evals) and mentions that it bills Vapi compute, implying caution. However, it does not explicitly state when not to use it or provide alternatives for different 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?

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds value by specifying 'real-time Twilio inventory lookup' and 'Mirrors GET /api/v1/phone-numbers/search', providing context beyond annotations.

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 front-loaded with key information. 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?

With 0 required parameters, 100% schema coverage, output schema present, and clear annotations, the description is complete enough. It conveys the purpose and nature of the tool adequately.

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?

Input schema coverage is 100% with descriptions for all parameters. The description does not add additional parameter semantics beyond what the schema provides, so baseline 3 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 clearly states the verb 'Search', resource 'carrier for phone numbers available to purchase', and purpose 'real-time Twilio inventory lookup'. It distinguishes from siblings like attach_number or buy_number.

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

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

The description implies usage for finding available numbers to purchase but gives no explicit guidance on when not to use or alternatives among siblings. No exclusion criteria mentioned.

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

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

Annotations indicate destructiveHint=true, which aligns with the description of sending a message. The description goes beyond annotations by explicitly mentioning compliance gates, rate limits, and message logging, as well as the behavior of honoring a lead's automation-pause state when lead_id is provided. This adds valuable behavioral context.

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

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

The description is extremely concise with two sentences. The first sentence covers purpose and behavioral context, and the second sentence lists required and optional parameters. No unnecessary words, and 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?

Given the tool has 4 parameters and no enums, the description covers purpose, required parameters, optional parameter with context, and behavioral aspects (compliance, rate limits, logging). It does not detail the output schema or error handling, but the presence of an output schema likely covers return values, so completeness is high.

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 100% with all parameters described, so baseline is 3. The description adds value by clarifying which parameters are required and explaining the purpose of the optional lead_id (attribution and respecting automation-pause state), enhancing understanding 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 clearly states the action (Send an outbound text message), the resource (from an agent's phone line to a recipient), and adds context about routing through the governed messaging API. It effectively distinguishes this tool from sibling tools like make_call or list_sms_messages.

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

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

The description mentions compliance gates, rate limits, and message logging, providing some context for when this tool should be used. However, it does not explicitly state when not to use it or provide alternatives. Since there is no other SMS sending tool among siblings, the guidelines are adequate but not fully 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?

Annotations already provide readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds the critical behavioral detail that the webhook secret is returned only on first creation, not on updates. This goes beyond annotations and helps the agent understand the side-effect difference between create and update.

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 concise at two sentences, front-loading the purpose and then adding the key return behavior note. Every word earns its place with no redundancy or fluff.

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

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

Given the presence of an output schema and detailed annotations, the description provides sufficient context. It covers the create vs update distinction and the secret return behavior. The tool has 6 parameters but all are well-documented in the schema, so the description need not repeat them. A minor gap is lack of guidance on when to set is_active or other common scenarios.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add significant extra meaning beyond the schema descriptions. It does provide a cross-reference to get_webhook for the supported event list, which is helpful but not essential.

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 creates or updates a business outbound webhook, specifying the key aspects (URL + subscribed events). It also mentions the return behavior (webhook secret only on first creation). This distinguishes it from sibling tools like delete_webhook and get_webhook.

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., when to create vs update, or when to use get_webhook to check current configuration). The description merely references the API endpoint but lacks contextual usage advice.

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

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

The description adds significant behavioral context beyond annotations: it explains that changes go through a governed update broker that maintains consent and audit trails, that every write is reversible (referencing get_change_history, list_config_versions, rollback_config), and that idempotency_key is required. This aligns with the annotations (destructiveHint, idempotentHint) and does not contradict them.

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 paragraph that is front-loaded with the primary action and then provides detailed behavioral and usage information. It is slightly long but every sentence contributes value. It could be broken into multiple sentences for readability but is otherwise 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?

Given the tool's complexity (18 parameters, nested objects, required authority), the description covers behavioral aspects (reversibility, audit trail, idempotency), references related tools (get_change_history, rollback_config, configure_agent_business_rules), and explains authority requirements. The existence of an output schema means return values are not needed in the description. It is complete for an AI agent to select and invoke correctly.

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

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

The input schema already has 100% description coverage for all 18 parameters, so the baseline is 3. The description groups parameters into categories (greeting, prompts, voice, model, etc.) and adds context like 'live runtime configuration' and reversibility, which adds marginal value but does not delve into parameter-level semantics 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 clearly states that the tool edits an agent's live runtime configuration and lists the specific fields it can modify (greeting, prompts, voice, model, etc.). It also distinguishes itself from the sibling tool `configure_agent_business_rules` by noting that the sibling is for a single operational-rules section, making the purpose very specific and 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?

The description provides explicit guidance on when to use this tool versus alternatives, stating 'For just a single named operational-rules section, prefer configure_agent_business_rules.' It also explains the requirements for idempotency_key, authority, and queue_for_approval, giving clear context for usage scenarios.

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