Criar verificação de antecedentes no ZapSign (consome créditos). Ação: create (data). Campos: country* (BR|CO|CL|MX|PE), type* (ex.: person | credit_person_br), user_authorized: true*, e um identificador: national_id | foreign_id.
[Flattened action: create]
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| account | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal a non-read-only operation (readOnlyHint=false), and the description adds valuable behavioral context: it consumes credits and requires user_authorized=true. It does not discuss side effects or auth prerequisites, but the added cost and authorization detail go beyond what the annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loaded with the main purpose. It contains redundancy with 'Ação: create' and '[Flattened action: create]' repeating the action, but overall the text is compact and scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the essential fields and enums, but the nested 'data' structure may have additional fields not documented, and there is no mention of the response format, error behavior, or the 'account' parameter. With no output schema and sparse annotations, some important context remains 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 input schema has 0% description coverage for the 'data' and 'account' parameters. The description compensates by listing the key fields inside 'data' (country* with allowed values, type* with examples, user_authorized, and identifier options), which is essential guidance for a nested object with no 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 it creates ('Criar') a background check ('verificação de antecedentes') in ZapSign, naming both the action and resource. It distinguishes itself from read-only siblings like zapsign_checks_get by explicitly indicating a write 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 specifies context by noting that the operation consumes credits ('consome créditos'), which is a meaningful usage caution. It lacks explicit alternatives or when-not-to-use guidance, but the purpose and cost side-effect make the expected usage clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct name and purpose, with clear separation between read and write actions. However, the high number of similarly-prefixed tools (e.g., zapsign_documents_write_*) and the overlap between create and create_from_template could occasionally cause misselection.
Domain tools follow a consistent zapsign_<resource>_<action> pattern, with writes marked by _write_. However, platform-level tools (authenticate, connect, marketplace) break the pattern, and zapsign_list_accounts deviates from the resource-prefix convention.
35 tools is excessive, especially since many are flattened actions from a smaller set of underlying operations. The inclusion of non-domain platform tools further inflates the count, making the tool list feel heavy and harder to navigate.
The core ZapSign domain is well covered: documents, signers, templates, webhooks, checks, and account management all have CRUD-like operations. Minor gaps exist, such as no listing endpoint for checks and no webhook list (due to API limitations), but these are not fatal for typical workflows.