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

No annotations are provided, so the description carries the burden. It lists returned fields but does not explicitly state that the operation is read-only or non-destructive. However, the context of confirming a connection implies safe 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, concise sentence that includes key data fields and use case. 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?

Given the tool has no parameters, no output schema, and no annotations, the description adequately informs the agent about what data is returned and the intended use. It is complete for a simple read-only account info 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 tool has zero parameters, and schema coverage is 100%. No parameter description is needed, and the baseline score is 4 for such cases.

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 returns Kommo account data (id, name, subdomain, currency, timezone) and its purpose is to confirm connection. It is distinct from sibling tools like kommo_get_lead or kommo_users.

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 includes 'Use para confirmar conexão' (use to confirm connection), providing clear context for when to use the tool. It does not explicitly discuss when not to use or alternatives, but given sibling diversity, this is sufficient.

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

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

With no annotations, the description should reveal behavioral traits like whether the note is appended or overwrites, or any side effects. It only states the action without additional 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 sentence, which is concise, but it lacks necessary detail for a tool with no annotations. It sacrifices completeness for brevity.

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

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

Given the complexity of 3 parameters, no annotations, and no output schema, the description is incomplete. It does not indicate what the tool returns or any success/failure conditions, making it insufficient for an agent to use 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 has 0% description coverage, but the description does not explain the parameters. It does not clarify that 'entity' can be leads/contacts/companies or that 'entity_id' is an integer ID. 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 clearly states the action 'Adiciona uma nota de texto' (adds a text note) and the target entities 'lead (ou contato/empresa)'. It distinguishes the tool from siblings which create entities or perform other 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?

No guidance on when to use this tool vs alternatives. Does not mention prerequisites (e.g., entity must exist) or exclude cases where a different tool (like create custom field) might be more appropriate.

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 only reveals that it is a batch operation. It does not disclose potential side effects, permissions required, atomicity, or error handling, which are critical for a mutation tool.

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

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

The description is a single, concise sentence that efficiently conveys the core function and batch capability without extraneous 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?

Despite having few parameters, the description omits important contextual details such as return values, error conditions, prerequisites, and whether the operation is additive or replaces the responsible user entirely.

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

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

Schema description coverage is 0%, and the description does not explicitly define the parameters beyond the tool name. While lead_ids and responsible_user_id are inferable, the description adds no additional semantic detail such as value constraints or format.

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 (change responsible), the resource (one or multiple leads), and the batch operation scope, distinguishing it from sibling tools like kommo_update_lead which is for single lead updates.

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 kommo_update_lead, or conditions under which it should not be used. The description lacks any 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 provided, so the description must fully disclose behavior. It only mentions optional result text but fails to describe side effects (e.g., whether the task is removed, if reversibility is possible, or any state changes beyond marking as completed).

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 efficiently conveys the core action and optionality. It is front-loaded and wastes no words, though it could include more context without becoming verbose.

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

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

Given the tool has two parameters and no output schema, the description is too minimal. It omits essential context like expected outcomes, error handling, or relationship to other task operations, making it incomplete for confident 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 0%, yet the description adds minimal parameter clarification: it mentions result is optional but does not explain task_id's purpose or format beyond the schema. The meaning of both parameters is insufficiently elaborated.

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 specifies the action ('marks as completed') and the resource ('task'), and includes optionality for result text. It effectively distinguishes from sibling tools like kommo_create_task and kommo_list_tasks.

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

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

No guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., task must exist) or contexts where this tool is appropriate or not.

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

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

With no annotations, the description must disclose behavioral traits. It only states the action (creates) without mentioning authentication requirements, side effects, rate limits, or whether the operation is idempotent. Critical details are missing.

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 (one short sentence) but lacks substance. It is not verbose, but the brevity sacrifices utility. Adequate for a simple tool, but could add critical context without sacrificing 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 no output schema and minimal input schema descriptions, the description is incomplete. It does not describe return values, error scenarios, or any behavioral constraints important for a CRUD 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 0%, and the description adds no meaning to the three parameters (name, responsible_user_id, custom_fields_values). It does not explain their purpose, format, or constraints, leaving the agent with minimal guidance.

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 'Cria uma empresa.' (Portuguese for 'Creates a company.') clearly states the verb 'creates' and the resource 'company'. It implicitly distinguishes from siblings like update_company or search_companies, though it lacks explicit differentiation.

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

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

No guidance is provided on when to use this tool versus alternatives (e.g., when to create a company vs. create a contact or search for an existing company). The description offers no context 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?

With no annotations, the description carries the full behavioral burden. It reveals that phone/email become custom fields automatically, which is a useful trait. However, it does not disclose other behavioral aspects such as potential side effects, authentication needs, or handling of duplicates.

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. It is front-loaded and to the point. However, it could include more details without becoming overly verbose.

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

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

Given 7 parameters and no output schema, the description is incomplete. It lacks explanations for most parameters, no example usage, and no context on prerequisites or integration with sibling tools.

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

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

Schema description coverage is only 14% (only name described), and the description adds no meaning for the other six parameters. The automatic custom field behavior is not parameter-specific. The 'custom_fields_values' structure and other fields remain unexplained.

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 a contact and notes automatic mapping of phone/email to custom fields. However, it does not explicitly differentiate from sibling tools like kommo_create_company or kommo_create_lead, though the name and action are distinct.

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

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

No guidance on when to use this tool vs alternatives, no prerequisites, and no mention of when not to use it. The description only states what it does 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, the description must disclose behavior. It lists allowed types but omits destructive potential, permission requirements, or side effects. Basic creation description only.

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

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

Two sentences, no redundancy, front-loaded with purpose. Every sentence is informative and necessary.

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

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

Given no output schema and 4 parameters, the description covers core creation but lacks details on uniqueness constraints, limits, or response. Sibling tools provide some 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?

Only 25% of schema parameters have descriptions. Description adds value for enums (explains when to use) and lists type options, but does not clarify name or entity beyond schema defaults.

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 a custom field in an entity and lists supported types. It implies creation as opposed to update (sibling kommo_update_custom_field), but does not explicitly differentiate.

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 guidance on using enums for select/multiselect types, but offers no when-to-use vs alternatives, 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 provided, so description carries full burden. It mentions optional contact linking but does not disclose side effects (e.g., duplicate handling), required permissions, or response behavior. Inadequate 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?

Single sentence covering key functionality. Concise and front-loaded, but could be more informative about other parameters.

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 8 parameters, no output schema, and no annotations, the description is too brief. It omits explanation of return values, behavior for missing optional fields, and interaction with other entities.

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 13% schema description coverage. The description explains that contact_name and contact_phone are for linking a contact and custom_fields_values for custom fields, but five parameters (price, status_id, pipeline_id, responsible_user_id) remain unexplained. Insufficient compensation for low 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 that the tool creates a lead, with optional contact linking and custom field setting. It distinguishes from siblings like kommo_create_contact (creates only contacts) and kommo_update_lead (updates existing).

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., kommo_create_contact for contacts only, or kommo_update_lead for modifying an existing lead). No prerequisites or context 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, and the description only states it creates a stage. It does not disclose behavioral traits such as idempotency, side effects, or specific permissions required. The description adds no detail beyond what is implied by the verb 'cria'.

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 redundancy. It lacks formal structure (e.g., bullet points) but is not verbose, making it easy to parse.

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

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

Without annotations or an output schema, the description is insufficient. It does not explain what the tool returns, error conditions, or how it integrates with other tools. For a creation tool, key context is missing.

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

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

The description mentions the key parameters (pipeline_id, name, optional sort/color) and their role, partially compensating for the schema's 50% description coverage. However, it does not explain the meaning of 'name' or 'pipeline_id' beyond their names, limiting 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 a new stage ('etapa') within a pipeline, using a specific verb and resource. However, it does not differentiate from other creation tools like kommo_create_lead or kommo_create_contact, though the name implies status 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 guidance on when to use this tool versus alternatives (e.g., why not use update_status or pipelines). The parenthetical 'desenvolver etapas' implies usage for stage development, but no exclusions 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 carries the full burden. It only states basic creation behavior without disclosing traits like idempotency, error handling, or authentication needs. For a creation tool, more detail 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 concise sentence that is front-loaded with the key action. However, it lacks depth that could be added without bloating.

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 no output schema and no annotations, the description is incomplete. It does not explain return values, prerequisites, or how parameters interact. For a 6-parameter creation tool, this is insufficient.

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 description coverage is only 33% (2 of 6 parameters have descriptions). The tool description adds no additional parameter meaning beyond the schema. It does not compensate for the low 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 'Cria' (creates), the resource 'tarefa' (task), and specifies it is linked to a lead or other entity with deadline and responsible person. This distinguishes it from siblings like kommo_list_tasks and kommo_complete_task.

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 creating tasks but does not explicitly state when to use it vs alternatives like kommo_complete_task or kommo_list_tasks. No when-not-to-use guidance or exclusions are provided.

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

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

No annotations are provided, so the description should cover behavioral traits. It states the tool lists custom fields, which implies a read-only operation, but does not explicitly confirm idempotency, rate limits, or authorization requirements. Some behavioral context is missing.

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

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

Two sentences with no unnecessary words. The first sentence states the function, the second gives a concrete use case. Highly 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?

With only one parameter and no output schema, the description covers the purpose and usage context adequately. It could optionally describe the return format, but it's not essential given the simplicity of 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?

The schema has one parameter 'entity' with enum values, but no descriptions. The description adds meaning by listing the options (leads/contacts/companies) and explains the parameter's role in specifying which entity's custom fields to list. This compensates for the 0% schema description 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 it lists custom fields for leads, contacts, or companies, and the purpose of finding field_id. It distinguishes from sibling tools like kommo_create_custom_field and kommo_update_custom_field by indicating this is a retrieval operation.

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

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

The description gives explicit guidance to use the tool to find field_id, which implies it should be used when you need to retrieve field identifiers. While it doesn't explicitly state when not to use it, the purpose is clear enough to differentiate from modification 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 present, so the description must fully disclose behavior. It states 'remove' (destructive), but does not specify if deletion is irreversible, if it requires certain permissions, or any side effects. 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?

A single sentence that is front-loaded with the action and resource, with no unnecessary words. It is concise and immediately informative.

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

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

For a simple one-parameter tool with no annotations or output schema, the description is just adequate. It identifies the parameter and purpose but lacks details on return values, error handling, or prerequisites, leaving the agent with 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?

The description explicitly mentions 'by destination URL', which directly corresponds to the single parameter 'destination', adding meaning beyond the schema (which has 0% description coverage). However, it does not specify required format, validation rules, or example values, so it only partially 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 'remove' (cancela) and the resource 'webhook', and specifies the deletion method 'by destination URL'. This distinguishes it from sibling tools like kommo_subscribe_webhook and kommo_list_webhooks.

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 or prerequisites. The description only implies that the destination URL is needed, but does not explain context such as checking if the webhook exists or ensuring correct URL format.

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?

Description implies read-only behavior ('feed', 'auditoria'), but does not explicitly state that the tool only reads data. No annotations exist to clarify. Could be more transparent about being a non-destructive operation.

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

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

Very concise (two sentences plus a list), front-loaded with key use case. Could benefit from slight structuring (e.g., bullet points for event types) but remains 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?

No output schema, and the description does not explain the format of returned events. For a list tool, this is a minor gap. However, given the complexity (8 params, no nested objects), the description covers enough for an agent to understand the tool's purpose and key filters.

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 75% of parameters with descriptions. The description adds valuable context: using created_by=0 for bot actions and listing common event types like lead_status_changed. Some parameters like 'to' and 'from' are only described in schema; no extra value from 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?

Describes a specific resource (event feed/audit log) and verb (get). Clearly states it is essential for understanding bot actions, distinguishing it from other tools in the set that do not provide event retrieval.

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

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

Provides explicit usage guidance: filter by created_by=0 for bot actions, lists common event types. However, does not mention when not to use this tool or alternative approaches, though no sibling event tool exists.

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 bears full responsibility for behavioral disclosure. It only mentions retrieving lead details and attaching notes, but does not confirm read-only nature, auth requirements, or any side effects. The tool name implies read access, but transparency is minimal.

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

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

The description is extremely concise with only two sentences, no redundant information, and front-loads 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 simple get tool with no output schema, the description adequately states that it returns complete details with contacts and optional notes. However, it leaves ambiguity about the exact response structure and does not mention that contacts are included by default.

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 50% (lead_id lacks description). The description adds no new semantics for lead_id and merely repeats the note_limit information already present in the schema. It does not compensate for the undocumented lead_id 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 explicitly states 'Detalhe completo de um lead por id, com contatos' which clearly indicates getting a lead by ID with contacts, distinguishing it from sibling tools like kommo_search_leads or kommo_update_lead.

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

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

No guidance is given on when to use this tool versus alternatives such as kommo_search_leads or kommo_get_events. The description only states what the tool does without any when/when-not or comparison 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 carry the full behavioral burden. It only states the linking action but does not disclose reversibility, idempotency, permission 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?

The description is extremely concise (one short sentence). It front-loads the purpose but lacks structure. While brevity is good, it omits critical details that could be added without becoming verbose.

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

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

Given 4 required parameters, no output schema, and no annotations, the description is insufficient. It does not mention return values, error conditions, or prerequisites (e.g., both entities must exist). A user would need to consult external documentation.

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

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

Schema coverage is 0%, meaning parameter descriptions are absent. The description only provides a high-level example but does not explain the meaning of 'entity' vs 'to_entity_type', or the role of the IDs. The enums are self-explanatory, but the description adds minimal 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 links one entity to another, with concrete examples (contact↔lead, company↔lead/contact). This distinguishes it from create/update tools, though it could explicitly differentiate from similar association 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?

No guidance is provided on when to use this tool versus alternatives like creating a new entity or updating existing ones. The description lacks context about prerequisites (e.g., entities must already exist) and 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 exist, so the description carries full burden. It only mentions filtering capabilities but does not disclose behavioral traits such as pagination, safety (read-only implied), auth needs, or rate limits. Schema has 0% coverage, so description should be more detailed.

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 superfluous words. It is front-loaded and gets straight 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?

Given 6 parameters, no output schema, and no annotations, the description covers only half the parameters. It lacks information on pagination, default sorting, or response format, leaving significant gaps for an effective tool invocation.

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

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

With 0% schema coverage, the description adds meaning for three parameters (responsible_user_id, entity_id/entity_type, is_completed) but ignores page and limit. It partially compensates for the schema gap.

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

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

The description clearly states it lists tasks and mentions filtering capabilities (responsible, entity, status). It distinguishes from sibling tools like kommo_create_task and kommo_complete_task, but does not explicitly differentiate from other listing tools.

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

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

The description implies usage for listing tasks with filters but provides no explicit guidance on when to use this tool versus alternatives like kommo_search_leads. No 'when not to use' or context provided.

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

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

With no annotations, the description carries full burden. It does not disclose behavioral traits such as being read-only or having no side effects. While listing is inherently non-destructive, it is not explicitly 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 concise (one sentence) and front-loaded. However, it is very brief and could benefit from additional structure or detail, though not excessively.

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 simplicity of the tool (no parameters, straightforward list), the description is mostly complete. However, lack of output schema or return format description mildly reduces completeness.

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

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

The tool has zero parameters, so baseline score is 4. The description adds no parameter information, which is acceptable as there are none to describe.

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 webhooks configured in the account, specifying the details (destination and subscribed events). It effectively distinguishes from sibling tools like subscribe/delete webhooks.

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. The description is minimal and does not provide context for selection among sibling tools.

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

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

With no annotations provided, the description carries full burden. It states a read-only listing operation, implying no side effects. However, it doesn't disclose other behavioral aspects such as authentication requirements, rate limits, or response format. The description is adequate but could be more explicit about the safety profile.

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

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

The description is extremely concise with two short sentences. The first sentence defines the output, and the second provides usage context. 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 no parameters and no output schema, the description provides essential information: what the tool returns (pipelines and stages with id, name, order) and when to use it. It could be slightly improved by noting that the output is a list or by providing an example, but it is largely complete for a simple listing 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?

There are no parameters, so schema coverage is trivially 100%. The description does not need to add parameter semantics. Baseline for 0 parameters is 4, which is appropriate.

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

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

Description clearly states it lists all pipelines and stages with id, name, and order. The specific verb 'lista' (lists) and resource 'funis e suas etapas' are unambiguous. The purpose is further clarified by indicating it's used to discover pipeline_id/status_id, distinguishing it from siblings like kommo_create_lead or kommo_search_leads.

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

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

The description explicitly says to use this tool 'para descobrir pipeline_id/status_id antes de criar ou mover leads.' This provides clear context for when to invoke it. While it doesn't explicitly state when not to use it, the guidance is sufficient given the sibling tools that perform other operations.

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

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

No annotations are provided, so the description carries full burden. It warns that PATCH/POST/DELETE methods alter data, which is critical. However, it lacks details on authentication, rate limits, error handling, or the response format, leaving gaps for an agent to invoke correctly.

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 highly concise, consisting of two sentences that efficiently convey purpose, usage context, and a critical warning. It is front-loaded and every sentence serves a clear function.

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?

Without an output schema, the description does not mention what the tool returns (presumably raw API response). It also omits details about error handling or required authentication scopes. Given the generic nature of the tool, the completeness is adequate but 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?

Schema coverage is 75% (method parameter lacks description). The description adds minimal extra meaning beyond what's in the schema (e.g., re-emphasizing relative path). The schema itself already provides examples and types, so the description's contribution is limited.

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 is a generic authenticated passthrough for Kommo API v4, intended for endpoints not covered by the other specific tools. It gives an example relative path and distinguishes itself from the many sibling tools that handle specific 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 explicitly states 'for anything not covered by the above tools,' providing a clear context for when to use this tool as a fallback. It warns that PATCH/POST/DELETE alter data, but does not explicitly advise against using it when a specific tool exists, though that is implied.

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

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

With no annotations, the description carries the full burden. It does not disclose behavioral traits such as read-only nature, return format, pagination defaults, or any 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 short sentence, which is concise but lacks structure. It front-loads the purpose but omits important details.

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

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

Given the complexity of a search tool with 3 parameters and no output schema or annotations, the description is severely incomplete. It fails to specify return value structure or pagination behavior.

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

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

Schema description coverage is 0%. The description only loosely references the query parameter with 'por texto' but does not explain the page and limit parameters.

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

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

The description clearly states it searches companies by text (nome, etc.), which distinguishes it from sibling tools like kommo_search_contacts and kommo_search_leads. However, it lacks specificity about which fields are searched beyond 'nome'.

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

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention when not to use it or any 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 bears the full burden. It only states that the tool searches contacts by text, failing to disclose read-only nature, permissions, rate limits, or behavior when no results are found. This is insufficient for an unannotated 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 with no extraneous words. It efficiently communicates the core purpose without repetition or filler.

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

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

Despite low complexity, the description lacks essential context such as output format (list of contacts?), pagination behavior, and error handling. Without an output schema, agents are left to infer return structure, which hinders 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?

With 0% schema description coverage, the description partially clarifies the 'query' parameter (by naming search fields) but entirely omits 'page' and 'limit' parameters, which are common pagination controls but remain unexplained.

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 'Search contacts by text (name, phone, email)' using a specific verb and resource, and distinguishes from sibling tools like kommo_search_companies and kommo_search_leads which operate on different 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 implies when to use (to search contacts by text) but provides no explicit guidance on when not to use it or alternatives. Given sibling tools for creating/updating contacts, the usage context is inferred but not elaborated.

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 only mentions return of leads with contacts, but lacks details on pagination (page/limit), search behavior (exact/partial match), or rate limits. More transparency needed.

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

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

Two concise sentences, front-loaded with action and filters. 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?

Missing explanation of pagination behavior and how to handle results beyond 'retorna leads com contatos embutidos'. No output schema, so more detail on return structure 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?

Adds meaning for 4 of 6 parameters: query (texto libre), pipeline_id (funil), status_id (etapa), responsible_user_id (responsável). Does not cover page and limit, but schema has defaults and max. With low schema coverage (17%), description compensates for most parameters.

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

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

Description clearly states 'Busca leads' and lists filtering criteria (query, funnel, stage, responsible). It distinguishes from sibling tools like kommo_get_lead (single lead) and kommo_search_contacts (contacts).

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 searching leads with filters, but no explicit when-to-use or when-not-to-use guidance. Does not mention 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 must disclose behaviors. It does not mention idempotency, validation, failure handling, or side effects. Only states the basic 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?

Two concise sentences, front-loading the purpose. Efficient, though could be slightly more structured with bullet points.

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 mention of return value (e.g., webhook ID, confirmation). No cross-reference to kommo_get_events for available events. Adequate for a simple tool but incomplete.

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

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

Schema coverage is 100%, but description adds valuable examples for settings (add_lead, etc.) and clarifies that settings is a list of events. This goes beyond the schema descriptions.

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

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

The description clearly states the tool subscribes a webhook to send Kommo events to a URL, with specific examples of events. It distinguishes from sibling tools like kommo_delete_webhook and kommo_list_webhooks.

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 (e.g., list vs subscribe vs delete). 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 provided, and the description only says 'updates an existing company'. It fails to disclose whether the update is partial, requires permissions, or has 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 very concise but sacrifices necessary detail. It is one sentence with no structure, leading to under-specification.

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 minimal description, the tool is poorly specified. Agent lacks context about expected behavior, return values, and 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 description coverage is 0% and the description adds no parameter details. The agent gets no help understanding what 'name', 'company_id', 'responsible_user_id', or 'custom_fields_values' mean.

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 'Atualiza uma empresa existente' clearly states the verb (update) and resource (existing company), distinguishing it from creation tools like kommo_create_company. However, it could be more specific about what aspects are updatable.

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 siblings such as kommo_create_company or kommo_update_contact. Missing context on prerequisites or alternatives.

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

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It merely states 'updates' without clarifying whether the update is destructive, requires permissions, or how existing fields are merged. The description lacks essential behavioral context 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 short sentence, which is efficient and to the point. However, it could be improved by adding more structure or bullet points for clarity.

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 6 parameters, no output schema, and no annotations, the description is too minimal. It does not cover return values, error handling, or the structure of custom_fields_values. The tool's complexity demands more context 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?

The description references three parameters (nome, responsável, campos custom) which correspond to name fields, responsible_user_id, and custom_fields_values. However, it does not explain the required contact_id parameter or the format of custom_fields_values. With 0% schema description coverage, the description adds some meaning but not enough to fully compensate.

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

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

The description clearly states the verb 'Atualiza' (Updates) and the resource 'contato existente' (existing contact), and lists specific fields that can be updated (nome, responsável, campos custom). This distinguishes it from sibling tools like create_contact or delete_contact.

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

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

No guidance is provided on when to use this tool versus alternatives such as kommo_change_responsible or kommo_update_lead. There is no mention of prerequisites, scenarios, 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 implies mutation ('atualiza') without detailing side effects, permissions, or reversibility. The example 'renomear' hints at a specific operation but 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 very short (one phrase), which is concise but at the cost of informativeness. It earns a baseline score due to brevity but lacks essential details.

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

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

Given no output schema, no annotations, and zero parameter coverage, the description is severely incomplete. It does not explain return values, entity options, or required field_id, making it inadequate for agent 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 description coverage is 0%, and the description does not explain any of the three parameters (name, entity, field_id). The phrase 'renomear, etc.' only weakly hints at the name parameter, leaving others undocumented.

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 'Atualiza um campo personalizado (renomear, etc.)' clearly states the action (update) and resource (custom field), giving an example of renaming. It is not a tautology, but lacks distinction from sibling tools like kommo_create_custom_field.

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. No conditions, prerequisites, or exclusions 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?

Without annotations, the description should disclose behavioral traits. It implies mutation but doesn't specify side effects, required permissions, or response behavior. The list of updatable fields provides some context, but important details are missing.

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 main action and lists key aspects 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?

For a tool with 7 parameters, no annotations, and no output schema, the description is too brief. It omits details on how parameters interact, constraints, and expected responses, making it insufficient for complex use cases.

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

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

Schema description coverage is 0% (no parameter descriptions in schema). The description mentions parameter names (status_id, pipeline_id, price, etc.) but does not fully explain their semantics or constraints (e.g., required relationships). It adds some meaning but not comprehensive.

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 updates a lead and lists updatable fields (stage, pipeline, price, responsible, name, custom fields). It distinguishes from siblings like create_lead and get_lead, but could be more explicit about the primary action.

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

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

No guidance on when to use this tool versus alternatives like kommo_change_responsible or kommo_create_lead. There is no mention of prerequisites or conditions, leaving the agent to infer usage.

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

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

With no annotations, the description carries full burden for behavioral disclosure. It only states the operation types (rename/reorder/recolor) but does not reveal side effects, required permissions, idempotency, or error behavior if the stage is missing. This leaves significant gaps for an AI agent.

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 that is concise and front-loaded. It avoids unnecessary words, though the use of slashes might be slightly ambiguous. Overall, it earns its place.

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

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

Given the tool has 5 parameters, no output schema, and no annotations, the description is insufficient. It only covers three parameter meanings and omits usage context, behavioral traits, and return behavior. The agent would have significant uncertainty.

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

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

The description maps three optional parameters (name, sort, color) to their respective actions, providing meaning beyond the raw schema. However, it does not explain the required parameters (pipeline_id, status_id) or any constraints. With 0% schema coverage, the description partially compensates but is incomplete.

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 updates an existing stage by renaming, reordering, or recoloring it. The verb 'renomeia/reordena/recolore' combined with 'etapa existente' specifies the action and resource, and distinguishes it from sibling 'kommo_create_status' which creates a new stage.

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

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

No guidance is provided on when to use this tool versus alternatives like creating a new stage. There is no mention of prerequisites, such as the stage needing to exist, or when renaming vs reordering vs recoloring is appropriate.

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, so the description carries full burden. It states the tool is a list operation with specific fields, implying read-only behavior. However, it does not disclose details like pagination, rate limits, or potential side effects, which are acceptable for a simple list 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?

Two short sentences, front-loaded with purpose and usage. Every word adds value with no redundancy.

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

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

No output schema, but the description explicitly lists returned fields (id, nome, email). With zero parameters and a straightforward purpose, the description is fully sufficient for an agent to understand and use 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?

The input schema has zero parameters, and schema description coverage is 100% (trivially). Baseline for 0 parameters is 4, and the description does not need to add parameter info.

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 it lists users with id, name, and email, and provides a specific mapping use case (name to responsible_user_id). This clearly differentiates it from sibling tools like kommo_account or kommo_search_contacts.

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

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

The description gives explicit guidance: 'Use para mapear nome -> responsible_user_id ao trocar responsáveis.' This tells when and why to use it, but does not mention when not to use or alternative tools.

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