Skip to main content
Glama

Dilligence — certidões de empresas

Ação em vários itens

bulk_items
Destructive

Uma ação em vários itens de uma vez: action="owner" (owner como em assign_item, ou null para tirar), "retry" (busca de novo as certidões que pararam ou não foram pedidas; gasta créditos quando saem), "na" (não se aplica, com reason) ou "remove" (tira da lista). Itens em que a ação não cabe são pulados e contados em skipped.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "diligence_id": "<diligence_id>",
      "action": "<action>",
      "item_ids": "<item_ids>"
    },
    "name": "bulk_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
ownerNo"me", o id de um membro (u:...) ou o e-mail de alguém de fora (com owner_name; recebe link de envio). Vazio tira o responsável.
actionYes
reasonNo
item_idsYes
owner_nameNoNome de quem é de fora
send_emailNoManda o link por e-mail (só se o usuário pediu)
diligence_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / owner / description
      Added value: +"\"me\", o id de um membro (u:...) ou o e-mail de alguém de fora (com owner_name; recebe link de envio). Vazio tira o responsável."
    • addedInput schema / properties / owner / type
      Added value: +"string"
    • addedInput schema / properties / owner_name
      Added value: +{
      +  "description": "Nome de quem é de fora",
      +  "type": "string"
      +}
    • addedInput schema / properties / send_email
      Added value: +{
      +  "description": "Manda o link por e-mail (só se o usuário pediu)",
      +  "type": "boolean"
      +}
  2. Changed4 schema fields changed
    • removedInput schema / properties / owner / description
      Removed value: -"\"me\", o id de um membro (u:...) ou o e-mail de alguém de fora (com owner_name; recebe link de envio). Vazio tira o responsável."
    • removedInput schema / properties / owner / type
      Removed value: -"string"
    • removedInput schema / properties / owner_name
      Removed value: -{
      -  "description": "Nome de quem é de fora",
      -  "type": "string"
      -}
    • removedInput schema / properties / send_email
      Removed value: -{
      -  "description": "Manda o link por e-mail (só se o usuário pediu)",
      -  "type": "boolean"
      -}
  3. Changed4 schema fields changed
    • addedInput schema / properties / owner / description
      Added value: +"\"me\", o id de um membro (u:...) ou o e-mail de alguém de fora (com owner_name; recebe link de envio). Vazio tira o responsável."
    • addedInput schema / properties / owner / type
      Added value: +"string"
    • addedInput schema / properties / owner_name
      Added value: +{
      +  "description": "Nome de quem é de fora",
      +  "type": "string"
      +}
    • addedInput schema / properties / send_email
      Added value: +{
      +  "description": "Manda o link por e-mail (só se o usuário pediu)",
      +  "type": "boolean"
      +}
  4. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavior: 'retry' consumes credits when certificates are actually issued, and items where the action does not apply are silently skipped and counted in 'skipped' — important context for a destructive bulk mutation. It still omits permissions, size limits and whether partial application is atomic.

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

Conciseness4/5

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

A single dense sentence front-loads the action list, which is the highest-value information for selection, and each clause about retry cost and skipped items earns its place. It is compact, though the nested parentheticals make it slightly harder to scan than a bulleted action breakdown would be.

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

Completeness3/5

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

For a destructive, non-idempotent bulk mutation with no output schema and only 43% parameter coverage, the description covers the action semantics and the skipped-items outcome but leaves gaps around permission requirements, maximum batch size, and what the response contains besides the skipped count. Adequate but not complete for a tool that can assign external owners and spend credits.

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

Parameters3/5

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

Schema coverage is only 43%, so the description must carry weight; it does explain the semantics of the 'action' enum values and ties 'reason' to the 'na' case, plus points 'owner' back to assign_item. But 'item_ids', 'diligence_id' and 'owner_name' receive no meaning beyond the schema, leaving roughly half the parameters undocumented.

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

Purpose4/5

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

The description opens with a specific verb+resource ('Uma ação em vários itens de uma vez') and enumerates the four action modes with their meaning, so an agent can tell this is the bulk counterpart of per-item actions. It falls short of a 5 because it never explicitly positions itself against the individual siblings (assign_item, retry_item, mark_not_applicable, remove_item) as a set.

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

Usage Guidelines3/5

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

Usage is implied through the per-action explanations: 'retry' re-fetches stopped/unrequested certificates, 'na' requires a reason, 'remove' takes items off the list, 'owner' assigns or clears. However, there is no explicit statement of when to prefer this bulk tool over calling the single-item tools in a loop, nor any prerequisite or exclusion guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.