Apagar arquivo anexado ao lead (DELETE /api/v1/leads/{leadId}/attachments/{id}). [write, altera dados]
Bulk support: accepts ids for batched execution.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| ids | No | ||
| body | No | ||
| leadId | Yes | ||
| 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?
The description explicitly states 'Delete' and 'write, altera dados', indicating a destructive write operation, but the annotations declare destructiveHint=false, which contradicts the action. This is a direct contradiction, warranting a score of 1 per the rules.
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, with the main purpose stated in the first sentence and a separate note for bulk support. It is front-loaded and contains no fluff 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?
Given the tool has 5 parameters, no output schema, and sparse annotations, the description is incomplete. It lacks explanations for 'body' and 'account', does not mention side effects or prerequisites, and omits return value details. The contradiction further 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?
Schema description coverage is 0%, so the description must compensate. It explains leadId and id/ids partially via the endpoint and bulk note, but ignores 'body' and 'account' parameters entirely. This leaves much of the parameter semantics 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 action: 'Delete file attached to lead' with the HTTP endpoint, distinguishing it from sibling tools like create and list. It specifies both the resource (attachment) and the operation (delete) clearly.
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 is given on when to use this tool versus alternatives, such as create or list for attachments. It implies usage for deletion but does not mention exclusions or conditions, and the bulk execution is only mentioned as a note without context on when to use it.
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.
Every tool maps to a distinct resource-action pair (e.g., leads_create vs businesses_create). Even nested tools like leads_activities_list are clearly scoped from general activities_list. No two tools appear to do the same thing.
All resource tools follow the exact pattern 'datacrazy_<resource>_<action>' with actions being create, get, list, patch, update, delete, plus a few composite verbs like finish_create or actions_win_create. The naming is uniform and predictable.
70 tools is far beyond the usual 3-15 range for an MCP server, making it overwhelming and unwieldy for agents. Although the scope is broad (full CRM), the sheer count exceeds the recommended threshold for effective tool discovery.
Most resources have full CRUD coverage (leads, activities, tags, lists, products, businesses, business_loss_reasons). Some gaps exist: attendants only have get/list, conversations lack delete/update, and pipelines are read-only. These are minor and workable, but not complete lifetime coverage.