Conecto

Get a file

files_get

Read-onlyIdempotent

One file's details (title, tags, type, correspondent, document date, notes, fields, where it came from, whether Conecto has read its words) and a fresh download link. With include_text, a text file (Markdown, CSV, JSON...) of up to 200 KB also comes back as it is; files_read_text returns the words of any file, scans included once read. Free.

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": {
      "file_id": "<file_id>"
    },
    "name": "files_get"
  }
}

Input Schema

Name	Required	Description
`file_id`	Yes	The file_id files_upload returned.
`link_hours`	No	How long the download link works, in hours (up to 168, one week).
`include_text`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive. The description adds real value beyond them: a time-limited download link, a 200 KB inline-text cap, and the fact that 'Free' applies (billing context). It does not state what happens if include_text is used on an unsupported type or whether the link expires silently.

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

Conciseness3/5

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

Front-loaded with the returned payload, which is the right priority, but the opening enumeration is a dense parenthetical that is hard to scan and reads more like a marketing blurb than a specification. 'Where it came from' and 'whether Conecto has read its words' are colorful but less precise than field names.

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?

With no output schema, the description does the work of describing the return payload, the link lifetime and the inline-text option. Missing: the default for include_text, error behavior for unknown or unreadable file_id, and no mention of cost or rate limits beyond 'Free'.

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 67%: file_id and link_hours are documented in the schema, but include_text has no schema description at all. The description partly compensates by explaining include_text's effect and its 200 KB limit, but it does not state the default (false) or which file types qualify beyond examples.

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

Purpose5/5

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

Specific verb (get) plus the resource and an enumeration of the metadata returned (title, tags, type, correspondent, document date, notes, fields, provenance, OCR state) plus the fresh download link and optional text payload. Clearly distinguishable from files_list and files_read_text.

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?

Explicitly routes to files_read_text for extracting words from any file, including scans, and names include_text as the way to get inline text. However it does not say when to use files_list instead, or that file_id comes from files_upload.

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

All Conecto tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?