Skip to main content
Glama
Sign In
aspa-mcp

aspa-mcp

by octos-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Enviar anexo

aspa_send_attachment
Destructive

Sends a local file up to 16 MB to a customer with an optional caption after explicit approval, enabling confirmed attachment delivery in a support conversation.

Instructions

Send a local file (image, PDF, etc., up to 16 MB) to the customer, with an optional caption. This is a real action visible to the customer or the team. Only call it after the user explicitly approved this exact action in the conversation.

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": {
      "contact": "<contact>",
      "path": "<path>"
    },
    "name": "aspa_send_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute path of a file in the user's home folder (not hidden folders), /tmp or a downloaded attachment.
indexNoIndex from aspa_list_conversations, only to tell apart contacts with the same name.
captionNo
contactYesContact name exactly as listed. Required for every action that changes a conversation.
conversation_idNoconversation_id returned by aspa_read_conversation. When given, the action is refused if the open conversation is a different one.
confirm_duplicateNoOnly true when the user explicitly wants to repeat the same message sent less than 2 minutes ago.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.8.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true; the description adds valuable context beyond them — that the action is externally visible to the customer/team, the 16 MB ceiling, and the explicit-approval requirement. It does not explain why the operation is destructive (irreversibility, no recall after sending) or what happens on failure/duplicate rejection.

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

Conciseness5/5

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

Two sentences, no filler: the first defines the action and its limits, the second states the behavioral consequence and the approval precondition. Front-loaded and every clause carries information.

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

Completeness4/5

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

For a six-parameter mutation tool with no output schema, the description covers the essentials an agent needs: what it sends, size limits, external visibility, and the approval gate. Gaps remain around duplicate-send behavior and failure outcomes, which matter given the destructive annotation.

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 83%, so the schema already documents path, contact, index, conversation_id and confirm_duplicate in detail; baseline is 3. The description only contributes the file-type and 16 MB size constraint tied to 'path', leaving caption and confirm_duplicate semantics entirely to the schema.

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?

States a specific verb and resource ('Send a local file (image, PDF, etc.) to the customer') plus a scope constraint (16 MB, optional caption), so an agent can distinguish it from aspa_send_message or aspa_send_template by payload type. It never names those siblings explicitly, so differentiation is inferable rather than stated.

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

Usage Guidelines4/5

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

Gives a strong, concrete precondition: 'Only call it after the user explicitly approved this exact action in the conversation.' That is a real when-to-use gate rather than generic advice. It does not name alternatives (e.g., use aspa_send_message for text) or state when-not-to-use beyond the approval gate.

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

Deploy Server

Other Tools