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

No annotations are provided, so the description carries the full burden. It states the integration is for agents but does not disclose behavioral traits such as whether the operation is reversible, if duplicate model names are allowed, what happens if the API base is unreachable, or any authentication requirements beyond the optional API key in schema. The description is too minimal to be transparent.

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

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

The description is a single brief sentence with no redundancy. It is front-loaded with the action and resource. However, it could be slightly more structured by including a second sentence for usage context. Still, it is concise and gets the main point across efficiently.

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

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

Given the absence of annotations and output schema, the description is incomplete. It does not explain the outcome (e.g., creates a model resource), how to reference the custom LLM in an agent, or any constraints like API compatibility. For a tool that adds an external integration, more context is needed for an agent to use it correctly.

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

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

Schema description coverage is 100%, so schema already documents all parameters. The description adds no additional meaning beyond 'Integrate a custom LLM'. For example, it does not explain that 'model_name' must be unique or that 'api_base' should be an OpenAI-compatible endpoint (though schema format hints at URI). Hence, 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 action ('Integrate') and the resource ('custom Large Language Model'), and specifies the purpose ('for use in agents'). It is distinct from most sibling tools which are about agents, calls, or other entities. However, it doesn't explicitly differentiate from the similar 'bolna_add_provider' tool, which might also add LLMs.

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. For example, it doesn't explain when to add a custom LLM via this tool versus using 'bolna_add_provider' or configuring an LLM directly in an agent. There are no exclusions or prerequisites 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?

With no annotations, the description must carry the full burden. It mentions 'securely add' but does not detail behavioral traits such as whether existing keys are overwritten, if validation occurs, or what the response indicates. The description lacks depth for a sensitive credential operation.

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

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

The description is a single, well-structured sentence that front-loads the key information (action, resource, examples) without unnecessary 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?

While the description covers the basic purpose, it lacks details on response format, error handling, or side effects. For a simple write operation with no output schema, it is adequate but could be more informative.

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 description adds marginal value by listing example provider types, but the schema already provides examples. The description does not compensate beyond that, meeting the baseline for high schema 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 action ('add'), the resource ('provider API key'), and provides examples of provider types (LLM, TTS, STT, telephony), making it easy to distinguish from sibling tools like 'bolna_add_custom_llm' which adds custom LLMs.

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 adding standard provider API keys but does not explicitly state when to use this tool versus alternatives like 'bolna_add_custom_llm' or 'bolna_list_providers'. No exclusions or conditions are provided.

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

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

No annotations provided, so description carries full burden. It states it's a write operation ('Add') but does not disclose behavioral traits such as validation, permissions required, or side effects. Missing important context like whether the trunk must exist beforehand.

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 12-word sentence, front-loaded with verb and resource. 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?

No annotations, no output schema. Description does not cover return behavior, prerequisites (e.g., trunk existence), or side effects. Incomplete for a mutation 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 baseline is 3. The description adds no extra meaning beyond the schema; parameters are self-explanatory but no additional clarification provided.

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

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

Description clearly specifies verb 'Add', resource 'DID phone number to SIP trunk', and purpose 'for inbound/outbound calling'. It distinguishes from sibling tools like remove or list.

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 adding numbers to existing trunks but lacks explicit guidance on when to use vs alternatives or when not to use. No exclusions or alternatives 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?

No annotations are provided, so the description must carry behavioral disclosure. It mentions 'atomically' implying transactionality, but omits other critical traits like idempotency, error handling, or limits. Lacks sufficient detail for a mutation tool.

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

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

One sentence, no redundant words. Efficient and front-loaded with key action and scope. Could be slightly improved with structure, but effective.

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 bulk mutation tool with nested array parameters and no output schema, the description is too sparse. It lacks details on success/failure responses, maximum array size, and preconditions (e.g., agent must exist). Inadequate for confident invocation.

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

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

Schema coverage is 100%, so baseline 3 applies. The description adds no extra meaning to parameters beyond what the schema already documents. No contradiction or missing info, but no added value.

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

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

The description clearly states the tool creates and links multiple dispositions atomically in one request. It distinguishes from the sibling 'bolna_create_disposition' via the 'multiple' and 'bulk' implication, but does not explicitly reference the alternative.

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

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

No explicit guidance on when to use this vs. the single-create alternative. The description implies bulk creation but offers no exclusions or context for choosing 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?

The description does not disclose any behavioral traits beyond the basic operation. No mention of side effects (e.g., cost, activation), return value, or required permissions. Annotations are absent, so the description carries full burden but falls short.

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 concise sentence that is front-loaded and contains no unnecessary words, meeting the efficiency criterion.

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

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

Given the absence of an output schema and annotations, the description is inadequate. It does not explain what happens after purchase (e.g., confirmation, returned data) or error scenarios. An agent would lack sufficient context to handle the tool's response.

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 schema already provides clear descriptions for both parameters (E.164 format for phone_number, provider examples for telephony_provider). The description adds no additional semantic value.

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

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

The description clearly states the action ('purchase a specific phone number') and the context ('for use with Bolna agents'), effectively distinguishing it from sibling tools like list or search operations.

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 (e.g., should the user first search for available numbers via bolna_search_phone_numbers?). No prerequisites or conditions 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?

No annotations are provided, and the description only mentions the action (create) without disclosing behavioral traits. It does not indicate what happens if an agent with the same name exists, whether the creation is immediate, any authentication requirements, or 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?

The description is a single, clear sentence with no unnecessary words or repetition. It is appropriately sized 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?

Given the complexity (18 parameters, no output schema, no annotations), the description is too brief. It does not explain return values (e.g., agent ID or object), nor does it provide any context about the creation workflow or expected outcomes.

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 input schema already documents all parameters. The description adds no new semantic information beyond the schema; the 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?

The description clearly states the tool's purpose: creating a new Bolna voice AI agent. It uses the verb 'create' and specifies the resource 'agent', and notes 'full configuration and system prompt', distinguishing it from sibling tools like bolna_patch_agent or bolna_list_agents.

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. It does not mention prerequisites, when it is appropriate to create vs update, or any disclaimers about naming conflicts.

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

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

No annotations provided, so description must carry the burden. It mentions uploading CSV and creating calls but does not disclose whether existing batches are affected, if there are rate limits, or if the batch executes immediately.

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

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

The description is a single sentence with no wasted words, front-loading the core 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 tool with 6 parameters, nested objects, and no output schema, the description is too minimal. It doesn't explain return values, execution behavior, or how the batch creation integrates with other operations.

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, so the description adds minimal extra meaning (e.g., CSV example). Baseline 3 is appropriate as it doesn't significantly enhance parameter understanding beyond what schema 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 what the tool does: create a batch call campaign by uploading a CSV of phone numbers. It uses specific verbs and resource, and distinguishes from siblings like bolna_make_call (single call) and bolna_schedule_batch (scheduling).

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. It doesn't mention that this is for large-scale campaigns vs. single calls, or any prerequisites like agent availability.

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

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

No annotations are provided, so the description carries the full burden. It fails to disclose any behavioral traits such as side effects (e.g., creating a linked resource), performance implications, or any constraints. The description merely states the action without further 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 a single, front-loaded sentence that clearly states the purpose. It is concise and free of unnecessary words, though it could be slightly expanded to improve completeness without losing brevity.

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

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

Given the complexity of the tool (11 parameters, nested objects, no output schema, no annotations), the description is insufficient. It does not explain the concept of a disposition, how the question/options interact, or what the agent linkage implies. This leaves the agent with significant gaps in understanding.

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 input schema already documents all parameters. The description does not add any additional meaning beyond what is in the schema, which is the baseline expectation.

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

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

The description clearly states the action 'Create a new call extraction disposition' and the specific resource, and it explicitly mentions linking to a Bolna agent, which distinguishes it from sibling tools like bolna_bulk_create_dispositions and bolna_update_disposition.

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

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no context for when not to use it. For example, it doesn't indicate if the agent must exist before creating a disposition.

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

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

No annotations provided. Description omits crucial behavioral details such as file size limits, processing time, auth requirements, error handling, or side effects on existing knowledgebases.

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, clear and direct, no redundant 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?

Lacks details on return value (e.g., knowledgebase ID), process duration, or whether creation is synchronous. Adequate for basic understanding but incomplete for a file-upload 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 covers 100% of parameters with descriptions. Description adds context on PDF and web URL methods, but does not significantly enhance 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?

Description clearly states the tool creates a knowledgebase via PDF upload or web URL ingestion, distinguishing it from sibling tools like delete, get, list.

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 creating knowledgebases from PDF or URL, but lacks explicit when-to-use, prerequisites, 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?

No annotations provided, so description carries full burden. Only mentions creation for inbound/outbound calling. Missing behavioral details like idempotency, reverse operation, required permissions, or 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?

Single sentence, front-loaded with key info. No filler or redundant clauses.

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 13 parameters (4 required), no output schema, and no annotations, the description omits critical context like return value, prerequisites, and behavioral outcomes. Incomplete for a complex creation 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 description coverage is 92% (high), so baseline is 3. Description adds no extra parameter insight beyond what the schema already documents.

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 verb 'Create' and resource 'SIP trunk' with context 'BYOT' and 'inbound/outbound calling via your own telephony provider'. Distinguishes from sibling update/delete/list 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?

Implies usage when creating a SIP trunk for own provider, but lacks explicit when-to-use, when-not-to-use, or alternatives (e.g., buying a number vs bring-your-own trunk).

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

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

No annotations are provided, so the description must disclose behavioral traits. It only mentions 'enterprise feature' and 'multi-tenant management', but does not explain side effects (e.g., creation of resources, isolation), required permissions, or what happens after creation (e.g., no explanation of the sub-account lifecycle).

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

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

The description is a single, concise sentence that front-loads the primary action. It is free of extraneous text, earning a high score, though it lacks structural elements like lists or bullet points which could improve scannability.

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

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

For a tool with 8 parameters and no output schema, the description is incomplete. It does not explain the return value, prerequisites, or typical usage flow. It provides minimal context beyond the basic purpose.

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 meaningful parameter descriptions. The description adds overarching context about enterprise and multi-tenancy but does not add new semantics beyond the schema. Baseline 3 applies as schema already does the lifting.

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

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

The description clearly states the verb 'Create' and the resource 'sub-account', and distinguishes it from sibling tools like delete, patch, list sub-account tools. It also specifies the context 'enterprise multi-tenant management', making the purpose unambiguous.

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

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

The description implies it's for enterprise multi-tenant scenarios, but does not explicitly state when to use this tool versus alternatives (e.g., when to create sub-account vs create agent). No exclusion criteria or prerequisites are 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?

The description indicates the action is permanent ('Permanently delete'), but it does not elaborate on side effects, required permissions, or any irreversible consequences beyond the schema. Without annotations, more transparency is expected.

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, well-formed sentence that front-loads the action and resource. Every word is necessary and no extraneous information is included.

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 delete operation with one parameter and no output schema, the description is minimally adequate. However, it could mention the irreversibility more explicitly. Annotations are absent, so the description does not fully compensate.

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

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

The schema has 100% description coverage for the only parameter (agent_id), and the description adds no additional meaning beyond what the schema already provides. 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 ('delete') and the resource ('Bolna agent'), with a specific identifier. It is distinguishable from sibling tools like create, update, or list agents.

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 other delete operations or when not to use it. The description lacks context about prerequisites or conditions.

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 are absent, so description carries full burden. It mentions 'Permanently delete' implying destructiveness, but lacks details on side effects (e.g., cascade deletions), authorization needs, or irreversibility. For a destructive operation, this is insufficient.

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

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

The description is a single efficient sentence with no waste, but given the destructive nature, it is too brief and could benefit from additional context while remaining 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?

Despite low complexity (1 required param, no output schema), the description lacks completeness by not explaining consequences, return value, or error handling. It is minimal but leaves gaps for an agent to understand full impact.

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

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

Only one parameter (batch_id) with schema description 'The batch ID to delete'. Schema coverage is 100%, and the description adds no extra meaning beyond the schema. 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?

The description clearly states 'Permanently delete a batch campaign by its ID', which specifies the verb (delete) and resource (batch campaign), distinguishing it from sibling tools like bolna_create_batch or bolna_stop_batch.

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 (e.g., stopping vs. deleting), no prerequisites or exclusions provided. The description only states the action without 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?

With no annotations provided, the description carries the full burden. It states that the action is permanent, which is useful, but does not disclose what happens if the disposition does not exist, whether a confirmation step exists, or any authorization requirements. The behavioral insight is minimal beyond the obvious destructive nature.

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 sentence with no extraneous 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?

For a simple deletion tool with one parameter and no output schema, the description is nearly complete. It conveys the core action and key input. However, it could improve by noting that deletion is irreversible or adding error behavior, but it is already sufficient for an agent to decide confidently.

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%, with the only parameter 'disposition_id' already described as 'UUID of the disposition to delete'. The description adds no additional meaning beyond restating 'by its ID'. Baseline of 3 is appropriate given full schema 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 verb 'delete', the resource 'disposition', and the identifier 'by its ID'. It distinguishes well from sibling tools like bolna_create_disposition, bolna_update_disposition, and bolna_list_dispositions.

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

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

The description implies the tool is for permanent deletion and should be used when a specific disposition must be removed. However, it does not explicitly state when not to use it or mention alternatives like bolna_bulk_create_dispositions, which might have related functionality. No guidance on prerequisites or consequences.

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?

States 'permanently delete', which implies irreversibility, but no annotations exist to cover destructive nature. Does not disclose required permissions or 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?

Single sentence, no wasted words. Front-loaded with 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?

Lacks information about return values, error cases, or success behavior. With no output schema, the description should provide more context about what happens after deletion.

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. The description adds no additional semantics beyond the schema's definition of knowledgebase_id. Baseline score 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?

Clear verb and resource: 'Permanently delete a knowledgebase'. It distinguishes from sibling deletion tools by specifying the resource type. However, it could be more explicit about the scope.

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 bolna_delete_agent or bolna_delete_batch. No prerequisites or exclusions 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?

Discloses key behavioral traits: permanent removal and billing stop. With no annotations, the description carries the full burden. It could add more detail about reversibility or dependencies, but the core effects are clear.

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

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

Single sentence that efficiently conveys purpose, input, and effect 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?

For a simple delete operation with one parameter and no output schema, the description is complete—states what it does, what it needs, and what happens.

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 has 100% coverage for the single parameter. Description does not add extra meaning beyond what the schema already provides, 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 the action (delete a purchased phone number by ID) and the consequences (stop billing, permanently remove). Distinguishes from siblings like bolna_buy_phone_number and bolna_list_phone_numbers.

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 when to use: to stop billing and remove a phone number. Mentions prerequisite (ID from bolna_list_phone_numbers) in param description. No explicit when-not-to-use but implied by the destructive nature.

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

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

With no annotations provided, the description carries full burden. It explicitly states permanence and cascading deletion of gateways and phone numbers, which is critical behavioral context. However, it omits authentication requirements, reversibility, or confirmation steps.

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

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

The description is a single, concise sentence that front-loads the action and includes scope. No wasted words; every phrase 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 low complexity (1 parameter), the description adequately explains the tool's purpose and effect. However, it does not mention return values, error conditions, or success confirmation, which would enhance completeness.

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

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

Schema coverage is 100% with the sole parameter 'trunk_id' documented in schema. The description adds no additional meaning or format guidance beyond the schema. Baseline 3 is appropriate since the schema already covers the parameter.

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

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

The description clearly states the action ('permanently delete'), the resource ('SIP trunk'), and the scope ('and all its associated gateways and phone numbers'). It is specific and distinguishes from sibling delete tools like bolna_delete_agent.

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

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, caution, or context for a destructive operation. It 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?

No annotations provided, so the description carries full burden. It transparently discloses the permanent, cascading deletion behavior. However, it omits details on error handling (e.g., non-existent sub-account) or reversibility, but 'permanently' covers the key trait.

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, well-structured sentence that front-loads the action and scope. Every word contributes 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?

For a simple delete tool with one parameter and no output schema, the description adequately covers the primary function and scope. It could mention that the action is irreversible (already implied) or list affected entities more explicitly, but it is sufficiently 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%, so the schema already documents the parameter. The description adds no additional meaning beyond what the schema's description ('UUID of the sub-account to delete') provides, earning a baseline score.

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

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

The description clearly states the verb 'delete' and the resource 'sub-account', and specifies the cascading effect on associated agents, batches, and executions. It effectively distinguishes from sibling delete tools that target specific entities.

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 versus alternatives like bolna_delete_agent or bolna_delete_batch. It lacks guidance on prerequisites or consequences, leaving the agent to infer usage 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?

No annotations are present, so the description must convey behavioral traits. It states 'retrieve', indicating a read operation, but fails to disclose error handling (e.g., 404 if agent not found), authentication requirements, rate limits, or whether any side effects occur. The description is minimally transparent.

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

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

The description is a single, front-loaded sentence with no wasted words. Every part is essential: verb, resource, identifier. 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?

For a simple retrieval tool with one parameter and no output schema, the description is adequate but lacks depth. It does not mention the structure of the returned configuration, error states, or permissions. It meets the minimum threshold but leaves gaps for an agent to infer.

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% (agent_id is fully described). The tool description does not add any new meaning beyond the schema; it merely restates the parameter. Baseline score of 3 is appropriate since the schema already provides sufficient parameter documentation.

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

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

The description uses a specific verb 'Retrieve' and clearly identifies the resource as 'full configuration of a specific Bolna agent by its ID'. It effectively distinguishes itself from sibling 'list' tools like bolna_list_agents by specifying retrieval of a single agent's full configuration rather than a summary list.

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 when needing the full configuration of one agent, but it does not explicitly state when to use this tool over alternatives (e.g., bolna_list_agents for summaries, bolna_get_batch for batches). No guidance on conditions or exclusions is provided.

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

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

No annotations are provided, so the description must carry the burden. It states what is retrieved (usage, consumption, billing) but does not disclose if this is a read-only operation, potential costs, pagination, or authentication requirements.

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

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

The description is a single, well-structured sentence that conveys the purpose efficiently without unnecessary 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 no output schema, the description does not specify the structure of the returned data. For a simple retrieval, it might be sufficient, but the lack of format details could leave the agent uncertain about the response.

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

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

There are no parameters, so the schema already covers everything. The description adds no confusion, but also does not add additional 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?

The description clearly states the action (Retrieve), the resource (usage, consumption, billing details), and the scope (ALL sub-accounts). It distinguishes itself from the sibling 'bolna_get_sub_account_usage' by emphasizing 'ALL'.

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 aggregate overview across sub-accounts, but does not explicitly state when to use this versus the sibling tool for a single sub-account. The contrast with the sibling name provides implicit guidance.

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

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

No annotations provided, so description carries full burden. It states the tool returns status and call counts but does not disclose read-only behavior, authentication needs, rate limits, or any other behavioral traits. Basic but not comprehensive.

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 of 10 words, front-loaded with purpose. No unnecessary words. 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?

For a simple tool with 1 parameter and no output schema, description adequately states core function. However, could be more complete by mentioning return format or that it is a read operation. Sibling tools exist but no guidance on differentiation.

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 single parameter 'batch_id' described. The tool description mentions 'specific batch campaign', aligning with schema. No additional semantic value 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?

Description clearly states 'Get detailed status and call counts for a specific batch campaign'. Verb 'Get' and resource 'status and call counts for batch campaign' are specific. Distinguishes from siblings like bolna_get_batch_executions and bolna_list_batches.

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 when you have a batch_id and need status/call counts, but no explicit guidance on when to use this vs alternatives (e.g., bolna_get_batch_executions, bolna_list_batches). No when-not or alternative tool references.

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

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

With no annotations, the description must disclose behavior. It mentions listing all executions but omits pagination behavior (page_size, page_number in schema) and what fields are returned. The agent cannot infer response structure or pagination logic.

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

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

A single, efficient sentence that directly conveys the tool's purpose. Could include pagination hint without significant bloat, but still 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?

The description is insufficient for a paginated list tool with no output schema and no annotations. It does not explain pagination defaults, returned data shape, or that batch_id is required (though schema marks it required). More context is needed for effective use.

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 for all three parameters. The description adds no extra meaning beyond the schema, meeting the baseline but not exceeding it.

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

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

The description clearly states it lists all individual call executions within a batch campaign, which is a specific verb+resource combination. It naturally distinguishes from sibling tools like bolna_get_execution (single execution) and bolna_list_agent_executions (agent-level).

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 for batch-level execution listing but lacks explicit guidance on when to use it vs alternatives (e.g., bolna_get_execution for a single execution) 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?

No annotations are provided, so the description carries the full burden. It only says 'retrieve' with no details on whether it requires authentication, side effects (none expected for a read), or what the response contains, which is insufficient 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 a single concise sentence that gets to the point. It is front-loaded with the action and resource. While succinct, it could be slightly more informative without losing conciseness.

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

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

Given the simple schema and no output schema, the description is adequate but missing context about the return value (e.g., returns a full disposition object) and error handling. It covers the basic purpose but not edge 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 coverage is 100%, baseline is 3. The description does not add any meaning beyond the schema; it doesn't explain the purpose of agen_id or that disposition_id is required, so no 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 'Retrieve a single disposition by its ID' clearly states the verb (retrieve), resource (disposition), and method (by ID), which is specific and distinguishes it from siblings like bolna_list_dispositions or bolna_create_disposition.

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

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

The usage is implied but not explicitly stated. The description does not mention when to use this tool versus alternatives (e.g., bolna_list_dispositions for multiple dispositions) or any prerequisites like having the disposition_id.

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

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns transcript and recording URL, which suggests read-only behavior. However, it does not explicitly state that no modifications are made, nor does it cover authentication needs or rate limits. For a simple read operation, the disclosure is adequate but not comprehensive.

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

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

The description is a single sentence with no unnecessary words. It front-loads the purpose and includes key details (transcript and recording URL). Every element is essential.

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 one parameter, no output schema, and no annotations, the description is fairly complete. It specifies what the tool returns (transcript and recording URL). However, it does not list all possible fields in 'full details', which could be slightly more explicit. Overall, it is sufficient for a simple retrieval 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?

The input schema has 100% description coverage for the single parameter execution_id. The description does not add any additional meaning beyond the schema; it only repeats the purpose of the tool. Since schema coverage is high, the baseline is 3, and the description does not improve upon it.

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

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

The description clearly states the tool retrieves full details of a call execution, specifying it includes transcript and recording URL. The verb 'Retrieve' and resource 'full details of a call execution' make the purpose specific and distinguishable from sibling tools like bolna_list_agent_executions and bolna_get_batch_executions.

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 when one needs full details of a specific execution, but it does not explicitly state when to use this tool versus alternatives like bolna_get_batch_executions or bolna_list_agent_executions. No when-not or alternative guidance is provided.

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

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

No annotations are provided, so the description must cover behavioral traits. It discloses the log contents but does not mention the read-only nature, required permissions, output size, or side effects. It lacks transparency on important behavioral aspects.

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

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

The description is a single, clear sentence with the verb upfront. No extraneous words, and every part 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 simple input (one parameter) and no output schema, the description covers the essential purpose. It could mention the format or size of logs, but for a raw logs retrieval tool, the description 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% with the execution_id parameter already described as 'The execution ID whose raw logs to retrieve.' The tool description adds no additional meaning beyond the schema, so a 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 ('Fetch') and the specific resource ('raw debug logs for a call execution'), and details the contents (LLM prompts, requests, responses, reasoning). It distinguishes itself from siblings like 'bolna_get_execution' by emphasizing 'raw' logs.

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 a debugging use case but does not explicitly state when to use this tool versus alternatives like 'bolna_get_execution' for summary logs. No when-not-to-use guidance is provided.

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

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

No annotations provided, so description carries full burden. It describes a read operation returning specific fields, but lacks mention of side effects, permissions, or pagination. Adequate but minimal.

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

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

Single sentence, direct, no unnecessary words. Front-loaded with verb 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?

Tool is simple with one parameter and no output schema; description sufficiently explains what is returned (ID, filename, status, creation time). Complete for a get 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 provides 100% coverage for the single parameter, describing it as 'The ID of the knowledgebase to retrieve'. Description adds no extra meaning beyond that.

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 verb 'Retrieve' and resource 'details of a specific knowledgebase', with specific fields listed. Distinguishes from siblings like bolna_get_agent which retrieves 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?

Implied usage: use when needing knowledgebase details. No explicit when/when-not or alternatives mentioned, though sibling names provide context.

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

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

With no annotations, the description must carry the full burden. It indicates a read operation ('Get full details'), which is appropriate, but does not disclose potential behavioral traits like authentication requirements, rate limits, or if any dependencies exist. For a simple retrieval tool, this is adequate but not enriched.

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. It efficiently conveys the tool's action, scope, and content of the response.

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

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

Given the tool's simplicity (one parameter, no output schema), the description adequately covers what the tool returns ('full details' including specific components). It could be more explicit about the absence of pagination or filtering, but for a single-trunk retrieval, it is sufficiently 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% with trunk_id described as 'The SIP trunk ID to retrieve'. The description adds context about the output (gateways, IP IDs, phone numbers) but does not enhance understanding of the parameter 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 retrieves full details of a single SIP trunk, specifying components like gateways, IP identifiers, and phone numbers. This distinguishes it from sibling tools like bolna_list_sip_trunks (which lists trunks) and create/update/delete operations.

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 for fetching a specific trunk's details, but lacks explicit guidance on when to use it versus alternatives (e.g., using bolna_list_sip_trunks first to get trunk IDs). No 'when not to use' or prerequisites are 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?

No annotations are provided, so the description must bear the full burden. It discloses the purpose but lacks information on auth requirements, error handling, or rate limits. The read-only nature is implied but not stated.

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

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

The description is a single, clear sentence with no unnecessary words. It is front-loaded 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 tool's simplicity (one parameter, no output schema), the description provides the core purpose but does not hint at the return value format or behavior in edge cases. It is minimally adequate.

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

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

Schema coverage is 100% with one parameter (sub_account_id) described in the schema. The description adds no new meaning beyond what the schema provides, so the 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 uses a specific verb 'Track' and specifies the resource 'usage, consumption, and billing details' for a specific sub-account. It clearly distinguishes from the sibling 'bolna_get_all_sub_accounts_usage' which operates on all sub-accounts.

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 a single sub-account but does not explicitly state when to use this tool over alternatives like bolna_get_all_sub_accounts_usage. No explicit when-not or prerequisites 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?

No annotations are provided, so the description must cover behavioral traits. It mentions the returned fields but does not disclose authentication requirements, side effects, 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?

Single sentence that is clear, front-loaded, and 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 no output schema and no annotations, the description adequately explains return data (name, email, wallet balance, concurrency limits). It is mostly complete for a simple read 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?

The input schema has no parameters and 100% coverage, so the baseline is 4. The description need not add parameter details.

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 Bolna account details, listing specific fields. It distinguishes itself from sibling tools that manage other entities like agents or batches.

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 fetching account info but lacks explicit guidance on when to use versus alternatives or when not to use.

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

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

No annotations are provided, so the description must carry full behavioral weight. It states 'list all call executions' but does not disclose any side effects, error handling, rate limits, or data limits. The mention of pagination is helpful but insufficient for a read operation.

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

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

The description is a single sentence that is clear, direct, and contains no unnecessary words. It is well front-loaded with the 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?

Given no output schema, the description should ideally mention what fields are returned or the structure of the response. It does not cover error behavior or edge cases. However, with three simple parameters, it is moderately 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% as all three parameters have descriptions in the schema. The description adds 'with pagination' but does not elaborate on the parameters beyond the schema, so value added is marginal. 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 'call executions for a specific Bolna agent', and the feature 'pagination'. It distinguishes from siblings like bolna_get_execution (single execution) and bolna_list_batches (different resource).

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 when you need to list executions for a specific agent, but does not mention when to use this tool versus alternatives like bolna_get_execution or bolna_get_batch_executions. No explicit when-not or context is provided.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It indicates a read/list operation scoped to the user's account, but does not mention authentication requirements, rate limits, or behavior for empty results. Adequate for a simple list function.

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 verb and resource front-loaded, no extraneous words, and clear structure. Every word is necessary and earns its place.

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

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

For a simple list tool with no required parameters and no output schema, the description is largely complete. It covers purpose and pagination. Could mention return format (e.g., list of agents), but this is a minor gap given the tool's 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%, with both parameters ('page_size' and 'page_number') already described. The description only adds 'with optional pagination', which is already implicit from the parameter definitions. The description adds minimal value beyond the schema.

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

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

The description explicitly states 'List all Bolna agents in your account with optional pagination', identifying the verb (List), resource (Bolna agents), and scope (your account, optional pagination). It clearly distinguishes from sibling tools like create, update, delete agents.

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 versus alternatives or when not to use it. The usage is implied from context, but no concrete exclusions or preferred scenarios are 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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. However, it does not mention key traits like pagination (e.g., whether it returns all batches or a page), ordering, side effects, or authorization requirements. The phrase 'list all' is ambiguous given the presence of pagination parameters.

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 9-word sentence with no extraneous information. Every word contributes to the core purpose, making it highly concise 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?

Given the absence of an output schema and annotations, the description should provide more context about the return format (e.g., fields returned, pagination metadata) and error conditions. The current description is insufficient for an agent to understand what to expect from the tool's output.

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%: agent_id, page_size, and page_number are already well-described in the schema (e.g., 'The agent ID whose batches to list', 'Number of batches per page'). The tool description adds no additional meaning or clarification beyond the schema, meeting the baseline expectation.

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

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

The description 'List all batch campaigns for a given Bolna agent' clearly specifies the verb (List), the resource (batch campaigns), and the scope (for a given agent). It effectively distinguishes this tool from sibling tools like bolna_get_batch or bolna_list_agents, which operate on different entities or actions.

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

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

The description provides no guidance on when to use this tool versus alternatives such as bolna_get_batch (for a single batch) or bolna_create_batch (for creating). There are no explicit when-to-use or when-not-to-use conditions, leaving the agent without decision-support information.

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

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

No annotations provided, but the description's 'list' verb implies read-only, non-destructive behavior. It does not disclose potential pagination or limits, but for a simple list operation, it is adequate.

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, short sentence that is front-loaded and contains no filler. 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 a simple list operation with one optional parameter and no output schema, the description fully covers what the tool does. No additional context is necessary.

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 described as 'Optional agent UUID to filter dispositions by'. The description adds no new semantic detail beyond this, 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?

The description clearly states 'List all dispositions for your account' using a specific verb and resource. It distinguishes itself from mutation siblings like create_disposition, delete_disposition, etc.

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 reading existing dispositions, but does not explicitly contrast with mutation tools or provide context on when to filter by agent. It is clear but lacks exclusionary guidance.

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

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

No annotations provided, but the description clearly indicates a read-only list operation ('List all knowledgebases'). It adds the behavioral context of returning status and metadata. Missing details like pagination or rate limits are minor given the simplicity.

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, well-structured sentence that conveys the tool's purpose and output. No superfluous 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?

Adequate for a parameterless list tool without an output schema. Specifies what is included in the response (status and metadata) but could be more precise about the return structure.

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

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

Zero parameters: baseline score of 4 per guidelines. The description adds no parameter information because none are needed.

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

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

Describes a specific action (list) on a specific resource (knowledgebases) with details about what is returned (status and metadata). Clearly distinguishes from sibling tools like create, get, or delete.

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 implicitly states when to use (to list all knowledgebases) and contrasts with single retrieval tools like bolna_get_knowledgebase. No explicit 'when not to use' or alternatives, but the context makes it 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?

No annotations provided, so description must convey behavior. 'List' implies a read-only operation, but no explicit statement about non-destructiveness, permissions, or side effects. The lack of annotations increases burden, but the description is minimally acceptable for a simple list.

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

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

Single sentence with 14 words, no fluff. Efficiently conveys 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 0-parameter list tool with no output schema, the description is complete. It fully informs the agent of the tool's action and scope.

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?

No parameters, so schema coverage is 100% trivially. Description adds no parameter info, but baseline is 4 for 0-parameter tools as per scoring guidelines.

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 all purchased phone numbers associated with the account, using specific verb 'List' and resource 'phone numbers'. It distinguishes from siblings like bolna_search_phone_numbers (which implies filtering) and bolna_buy_phone_number (creation).

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 like bolna_search_phone_numbers. The description implies it's for a complete list without filtering, but does not state exclusions or prerequisites.

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

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

With no annotations, the description discloses the read-only nature of the tool. It is a simple list operation with no side effects, which is sufficiently transparent for its simplicity. No contradictions with annotations as none exist.

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

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

The description is a single sentence that conveys the entire purpose without any fluff. It is concise 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?

Given the tool's simplicity (no parameters, no output schema), the description is complete enough. It explains what the tool returns and its scope. A brief mention of return format could improve it but is not necessary.

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

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

There are no parameters in the schema, and the description does not need to add parameter semantics. The baseline for zero parameters is 4, and the description does not detract from that.

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 'providers', and defines the scope as 'all configured in your Bolna account'. This effectively distinguishes it from sibling tools like bolna_add_provider and bolna_remove_provider.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives, such as before adding or removing providers. The usage context is implied but not stated.

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

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

No annotations provided, so the description must carry the behavioral burden. It states 'List' implying read-only, but does not disclose any side effects, error cases (e.g., invalid trunk_id), pagination, or return format. Minimal 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?

Single sentence that is front-loaded with the action and resource. No unnecessary words, concise and to the point.

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 required parameter and no output schema, the description provides the essential purpose but lacks additional context such as return type, read-only nature, or any restrictions. It is adequate but not complete.

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

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

Schema coverage is 100% and the parameter 'trunk_id' is described in the schema. The description adds no extra meaning beyond the schema; it merely references the trunk. Baseline 3 is appropriate as the schema already documents the parameter well.

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

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

The description clearly states the action (list) and the resource (phone numbers associated with a SIP trunk). It distinguishes from sibling tools like bolna_list_sip_trunks (which lists trunks, not numbers) and bolna_list_phone_numbers (which likely lists all phone numbers, not scoped to a trunk).

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. Does not state that it requires a trunk_id or that it is for a specific trunk only. Lacks context like 'Use this when you need numbers for a particular trunk.'

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

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

No annotations provided, so the description carries the burden. It only says 'list all', which is read-only, but fails to disclose any other behavioral traits like pagination 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?

Single sentence, direct, no fluff, front-loaded with the 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?

Adequate for a simple list operation with one optional parameter, but lacking output schema or any further context about the response format or limitations.

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 'active_only' has a description in the schema. The tool description adds no extra 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?

The description clearly states the verb 'List' and the resource 'SIP trunks', and distinguishes it from sibling tools like 'bolna_get_sip_trunk' for a single trunk.

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 instead of alternatives or when not to use it. The description only states what it does.

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

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

No annotations are provided, and the description does not disclose any behavioral traits beyond the purpose. It lacks information on read-only nature, authentication requirements, rate limits, or any side effects. The agent has no additional 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 a single concise sentence that conveys the essential purpose with no redundancy. 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 no parameters, the description is adequate but lacks information about the return format or pagination. Since there is no output schema, the agent does not know what fields are returned, which could be improved.

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

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

There are no parameters, so schema coverage is 100% trivially. The description adds no parameter information, but none is needed. Baseline score of 4 is appropriate for zero-parameter tools.

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 all sub-accounts linked to the main organization account. It uses a specific verb 'list' and resource 'sub-accounts', and distinguishes it from sibling tools like bolna_list_agents.

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 over alternatives is provided. While it is the only list sub-accounts tool, the description does not mention exclusions or context for use. Implied by tool name but not 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?

No annotations are provided, so the description must convey behavioral traits. It mentions pagination and optional filtering, but does not disclose whether the operation is read-only, any required permissions, or what happens with no results. Minimal but adequate for a list operation.

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

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

The description is a single, clear sentence that conveys the core functionality without any redundant words. It is front-loaded with key 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?

Given the lack of output schema, the description could mention what the return value contains (e.g., list of violation objects), but it does not. However, the tool is simple and pagination is indicated, so it is moderately 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 description adds little beyond the schema. It reiterates the status filter but does not provide additional context for page_size and page_number. 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 uses a specific verb 'Retrieve' and clearly identifies the resource as 'a paginated list of call violations'. It distinguishes from sibling list tools by specifying the resource type (violations) and includes the optional status filter.

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

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

The description states what the tool does but does not provide explicit guidance on when to use it versus alternatives, nor does it mention any prerequisites or limitations. Since it's a simple list operation, the lack of guidance is moderate but acceptable.

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

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

No annotations are provided, so the description carries the full burden. The verb 'List' implies a read-only operation, but the description does not explicitly state that it is non-destructive or safe. It also does not disclose any rate limits or pagination behavior.

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

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

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose and the output details. No unnecessary 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?

For a simple listing tool with two optional filter parameters and no output schema, the description is reasonably complete. It mentions the output fields (provider, language, accent). However, it could mention if there is pagination or a default 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 description coverage is 100% for both parameters (language and provider), so the schema already documents them adequately. The description adds no additional parameter-level detail beyond what the schema 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 lists all available voices for the account, specifying that it includes provider, language, and accent details. This distinguishes it from sibling list tools like bolna_list_agents or bolna_list_batches.

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

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

The description provides no guidance on when to use this tool versus other list tools or alternatives. It does not mention prerequisites, filters, 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?

No annotations are provided, so the description must fully disclose behavioral traits. It only states the action without mentioning any side effects (e.g., cost, blocking, state changes), required permissions, or limitations. The description is insufficient for an agent to understand implications.

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

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

Single sentence, concise and to the point. No wasted words. Front-loaded with the core action.

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

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

No output schema, and the description does not explain what the tool returns (e.g., a call ID) or its side effects. For a tool with 10 parameters and no annotations, the description is too sparse to be fully actionable.

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% — all 10 parameters have descriptions in the input schema. The tool description does not add extra meaning beyond the schema. Baseline 3 is appropriate since the schema already documents parameters adequately.

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

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

The description states 'Initiate an outbound voice call using a Bolna agent to a specified phone number', which clearly identifies the verb (initiate), resource (outbound voice call), and specific actors (Bolna agent, phone number). It is distinct from sibling tools that handle agents, batches, or configurations.

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 (e.g., bolna_schedule_batch, bolna_stop_call). No prerequisites, conditions, or exclusions mentioned. The description is purely declarative.

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

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

With no annotations, the description carries full burden. It states partial update (mutation) but does not disclose idempotency, permission requirements, side effects, or return behavior.

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

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

Single sentence, front-loaded with key information, no unnecessary 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?

No output schema exists, and the description does not mention return values or expected output. For a mutation tool, this is a gap. Sibling tools exist but no comparative guidance provided.

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 are already documented. The description adds no new meaning beyond listing a few fields (name, welcome message, webhook URL).

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 partially updates specific fields of a Bolna agent, listing examples (name, welcome message, webhook URL). This distinguishes it from create, delete, get, and full-update tools among siblings.

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

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

The description implies use for partial updates, but does not explicitly contrast with bolna_update_agent or provide when-not-to-use scenarios. No prerequisites or alternatives are 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?

The description indicates the tool updates only provided fields (partial), which is useful. However, with no annotations, it misses details on side effects, authorization requirements, or idempotency, leaving the agent somewhat in the dark.

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 no redundancy, front-loaded with purpose. 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?

Adequate for a simple update tool, but lacks explanation of response (no output schema), error cases, or behavior when no fields are provided. Could be more complete given the absence of annotations.

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 description adds little beyond naming the fields. It mentions 'name or concurrent call limit,' but does not elaborate on format, constraints, or behavior when both are omitted.

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 a partial update on a sub-account, specifying the updatable fields (name, concurrent call limit). This distinguishes it from sibling tools like create_sub_account or delete_sub_account.

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

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

The description provides basic context (partial update) but lacks explicit guidance on when to use this tool versus alternatives, such as when a full update or complete replacement is needed.

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

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

No annotations are provided, so the description carries full burden. It only states the action without disclosing side effects, reversibility, or what happens if the key is in use. Minimal depth beyond the action itself.

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

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

A single, front-loaded sentence of 12 words with no superfluous information. Highly efficient and direct.

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

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

Given the low complexity of the tool (one required parameter, no output schema), the description is mostly adequate. It clearly states the action and the parameter is well-documented in the schema. However, it lacks mention of expected response or error conditions.

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

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

Schema coverage is 100% for the single parameter, providing its description and example. The tool description adds the context 'previously added' but not additional parameter semantics, 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 states the verb 'Remove' and the resource 'provider API key' from the user's account, clearly distinguishing it from sibling tools like bolna_add_provider or bolna_list_providers. 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?

The description implies usage when one wants to remove a previously added provider API key, but does not explicitly state when to use or not use this tool versus alternatives, nor provide prerequisites.

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

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does disclose the important side effect of removing agent mapping, but lacks details such as reversibility, permission requirements, or success/failure behavior.

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

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

The description is a single sentence that conveys the core action and a key behavioral note (removing agent mapping). It is front-loaded and contains no superfluous 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?

The tool has no output schema and no annotations. The description does not specify what the tool returns (e.g., success confirmation, error types, or updated trunk object). Given the destructive nature and lack of complementary structured information, the description is incomplete for an agent to confidently use.

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 provides 100% coverage with clear descriptions for both parameters (trunk_id and phone_number_id). The tool description adds no additional semantic meaning beyond what the schema already offers, so the 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 'Remove' and the resource 'a phone number from a SIP trunk', and also notes the side effect 'also removes any agent mapping'. This distinguishes it from sibling tools like bolna_add_sip_trunk_number and bolna_list_sip_trunk_numbers.

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 the tool (to remove a phone number from a SIP trunk) but does not provide explicit guidance on when not to use it or mention alternatives (e.g., deleting the phone number entirely or unlinking an agent separately). No contextual cues for decision-making.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as whether the batch must be in a specific state, whether rescheduling is allowed, or timezone handling. The description relies solely on the name and schema, adding minimal 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 a single, front-loaded sentence that efficiently communicates the tool's purpose without unnecessary words or redundancy.

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

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

For a simple scheduling tool with two required parameters and no output schema, the description adequately covers the core functionality. It could be slightly improved by noting what the response indicates (e.g., success/failure), but is sufficiently complete for selecting the 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 descriptions for both parameters. The overall description echoes the schema ('previously created batch' for batch_id, 'specific date and time' for run_at) without adding new interpretive value, so it meets the baseline.

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

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

The description clearly states the action (Schedule), the resource (a previously created batch), and the context (to run at a specific date and time). It effectively distinguishes this tool from siblings like bolna_create_batch and bolna_stop_batch.

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 after creating a batch, but does not explicitly state when to use or not use this tool compared to alternatives. The context is clear but lacks explicit guidance on 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?

No annotations are provided, so the description carries the full burden. It correctly indicates a read-only search operation, but does not disclose authorization needs, rate limits, or potential side effects. Minimal but accurate.

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, direct, and front-loaded with the core action and filters. 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?

The description covers purpose and filters but lacks details about result format, pagination (limit parameter present), or any behavioral nuances. For a search tool with no output schema, more context would be helpful.

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 adequate parameter descriptions. The description echoes filter dimensions without adding new semantic depth beyond the schema, earning a baseline score.

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

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

The description uses a specific verb 'search' and resource 'available phone numbers to purchase', clearly distinguishing this from sibling tools like bolna_buy_phone_number (purchase) and bolna_list_phone_numbers (list owned numbers). The filters (country, area code, pattern) are explicitly stated.

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

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

The description implies this tool is for discovery before purchase but does not explicitly state when to use versus alternatives, nor provides prerequisites or exclusions. Guidance is implicit but not actionable.

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

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

No annotations provided, so the description must carry the burden. It states the tool associates an agent with a phone number, but does not disclose whether it overwrites existing associations, requires special permissions, or has any side effects. Minimal behavioral context is given.

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

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

The description is a single concise sentence that front-loads the action. It could benefit from a bit more context (e.g., 'overwrites any existing assignment'), but overall it's efficient and to the point.

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 tool with two plain string parameters and no output schema, the description is adequate but minimal. It does not explain whether the association is persistent, what happens in case of errors, or that the sibling tool unlink exists. Slightly incomplete for full context.

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

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

Schema description coverage is 100%; both parameters have clear descriptions in the schema. The tool description adds no additional meaning beyond what the schema already provides. 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 a specific verb 'Associate' and clearly identifies the resources (Bolna agent, phone number) and the outcome (handles inbound calls). It distinguishes well from siblings like bolna_unlink_inbound_agent (the reverse action).

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

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

The description implies when to use (to set up inbound call handling) but lacks explicit guidance about prerequisites, when not to use, or alternatives. No mention of unlink or other related 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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only states the effect (prevent execution) but does not disclose whether the action is irreversible, any permission requirements, rate limits, or what happens to calls already in progress. This is insufficient for a mutation tool.

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

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

The description is a single sentence that directly conveys the tool's purpose without any extraneous words. It is front-loaded 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?

For a simple tool with one parameter and no return schema, the description covers the basic operation. However, it lacks information on error handling (e.g., invalid agent_id), confirmation of success, and edge cases (no queued calls). This leaves some gaps.

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

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

Schema coverage is 100% with the single parameter 'agent_id' described as 'The unique ID of the agent whose queued calls to cancel'. The tool description repeats this same information, adding no additional meaning or detail 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 action (stop) and resource (all queued calls for a specific Bolna agent) with the explicit purpose of preventing their execution. It distinguishes itself from sibling tools like 'bolna_stop_batch' and 'bolna_stop_call' by specifying the scope is agent-level queued 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 provides clear context that this tool is for stopping queued calls of a specific agent. While it does not explicitly mention when not to use it or list alternatives, the name and description imply its use case sufficiently, and sibling tools cover different scopes.

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

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

With no annotations provided, the description bears full responsibility. It discloses the core action (stop and cancel), but lacks details on side effects (e.g., irreversibility, impact on ongoing calls) or required permissions. The description is adequate but not thorough.

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

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

The description is a single sentence with no extraneous words. It efficiently conveys the purpose and action, earning its place without waste.

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 tool with one parameter and no output schema, the description sufficiently explains the purpose and effect. It could be more complete by mentioning what happens after stopping (e.g., status change), but is adequate for basic use.

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 is straightforward ('The batch ID to stop'). The tool description does not add any additional meaning or constraints beyond what the schema provides, meeting the baseline expectation.

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 'Stop' and the resource 'batch campaign', with the specific action 'cancel all pending calls'. It effectively distinguishes from sibling tools like bolna_stop_call (single call) and bolna_stop_agent_queued_calls (queued calls of an agent).

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, when not to use, or suggest other tools like bolna_get_batch to check status first.

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

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

No annotations are provided, so the description carries full burden. It mentions 'immediately terminate' but lacks details on side effects, reversibility, or prerequisites. More behavioral context would be beneficial.

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 unnecessary words. It conveys the essential information efficiently.

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

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

Given the tool's simplicity (one parameter, no output schema), the description is mostly adequate. It could add a note about the call needing to be active or reference sibling tools, but it is sufficient for basic use.

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 parameter 'execution_id' is already well-documented in the schema. The description adds no extra meaning beyond the schema's description.

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

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

The description clearly states the verb 'terminate' and resource 'active call', and specifies the identifier 'execution ID'. It distinguishes from sibling tools like 'bolna_make_call' and 'bolna_stop_agent_queued_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 when to use (to stop an active call) but does not explicitly mention when not to use or provide alternatives like 'bolna_stop_agent_queued_calls' or 'bolna_stop_batch'.

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

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

No annotations are provided, so the description alone must disclose behavioral traits. It only mentions optional evidence but does not state what happens upon submission (e.g., irreversible, requires permissions, 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?

A single, compact sentence that efficiently communicates the tool's purpose and key optional feature without any superfluous 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?

Despite 4 parameters and no output schema, the description lacks details on return value, state changes, or prerequisites. It is minimally adequate but leaves significant context gaps for an AI agent.

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%, providing baseline 3. The description adds value by clarifying that 'evidence_base64' should be base64-encoded (e.g., PNG or PDF) and notes the default filename, aiding correct usage.

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 ('Submit') and the resource ('violation'), and specifies the optional evidence file, distinguishing it from siblings like 'list_violations' or 'create_disposition'.

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, nor any prerequisites or exclusions. For example, it doesn't mention that you need to first list violations or that there is a related disposition tool.

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

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

No annotations are provided, so the description must carry the full burden. It mentions 'preview extraction results' suggesting a read-only operation, but does not confirm non-destructiveness, required permissions, or whether results are saved. Lacks explicit behavioral traits.

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 that efficiently conveys the tool's purpose and scope. No redundant words, well-structured, 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?

With 2 parameters, no output schema, and no annotations, the description provides adequate context for a testing tool. However, it could benefit from mentioning the return format (e.g., a preview object) or confirming that no data is mutated.

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 parameter descriptions. The description adds context by stating it tests 'all dispositions' associated with the agent, which goes beyond the schema's individual parameter descriptions.

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

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

The description clearly states the verb 'Test', the resource 'dispositions linked to an agent against a call transcript', and the outcome 'preview extraction results'. This distinguishes it from siblings like bolna_create_disposition or bolna_get_disposition.

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 previewing extraction results before deployment but does not explicitly state when to use this tool over alternatives like bolna_list_dispositions or bolna_get_disposition. No when-not-to-use or alternative 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?

No annotations are provided, so the description carries the full burden. It only states the basic action without disclosing behavioral traits such as reversibility, effects on ongoing calls, or permission requirements.

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

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

The description is a single concise sentence (13 words) that front-loads the verb and resource. Every word is meaningful and there is 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?

For a low-complexity tool with one parameter and no output schema, the description is minimally adequate. However, it lacks behavioral details such as success indication or side effects, which would be helpful.

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%, and the schema already describes the parameter. The description adds context about the tool's purpose but does not add further meaning to the parameter beyond what the schema 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 ('Remove a Bolna agent from a phone number') and the goal ('to disable automated inbound call answering'). It uses a specific verb and resource, and distinguishes from the sibling 'bolna_set_inbound_agent'.

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 guidance on when to use this tool versus alternatives like 'bolna_set_inbound_agent', nor does it mention prerequisites (e.g., the phone number must have an agent linked) 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?

No annotations provided; the description only states 'update' without disclosing whether it merges or replaces, permissions required, or side effects. Insufficient for a mutation tool with 13 parameters.

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, but lacks structured formatting. Efficient yet minimal.

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 13 parameters, no output schema, and no annotations, the description is too minimal. It does not explain return values or confirm success, leaving gaps for 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% with all parameters documented. The description adds no extra value beyond the schema, 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 action (Update) and the resource (existing Bolna agent's configuration and/or system prompt). It distinguishes from create/delete agents but leaves ambiguity with bolna_patch_agent.

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 bolna_patch_agent or bolna_create_agent. Missing prerequisites or context for updating.

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 discloses the copy-on-write behavior when scoped to an agent, which is a key behavioral trait. However, with no annotations, it fails to mention other important aspects like permissions, idempotency, or error handling.

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 at one sentence, which is a strength. However, it could be slightly more structured to separate the main action from the behavioral note.

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 (11 parameters, no output schema, no annotations), the description is incomplete. It does not explain update semantics (partial vs full), return values, or error conditions, leaving significant gaps for the agent.

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

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

Schema description coverage is only 18%, and the tool description adds no additional parameter semantics beyond what is already in the schema. The remaining 9 parameters are left undocumented, forcing the agent to rely on naming conventions.

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 ('update a disposition') and the resource, which distinguishes it from create or delete tools. However, it does not elaborate on what aspects can be updated beyond the schema fields.

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 versus alternatives like create or delete. The context is implied but lacks explicit guidance on 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?

No annotations are provided, so the description must fully convey behavioral traits. It only states 'partially update' and lacks details on side effects (e.g., immediate vs. queued updates), authentication requirements, rate limits, or error handling (e.g., what if trunk_id does not exist).

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 directly conveys the core action. No unnecessary words or repetition.

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

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

Given 7 parameters, no output schema, and no annotations, the description is too brief. It omits failure modes, required permissions, return values, and confirmation of operation success. The tool is complex enough to warrant richer 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?

The input schema has 7 parameters with only trunk_id described. The description adds 'only included fields are changed', which clarifies partial update semantics but does not explain the meaning of each field (e.g., inbound_enabled). With 14% schema coverage, the description insufficiently compensates.

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 ('Partially update') and the resource ('existing SIP trunk'), distinguishing it from sibling tools like create, get, list, and delete. The phrase 'only included fields are changed' further clarifies the partial update behavior.

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

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

The description indicates that it modifies only specified fields, implying a patch operation. However, it does not explicitly state when to use this tool versus alternatives (e.g., recreating the trunk for full updates) or any prerequisites (e.g., trunk must exist).

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