Skip to main content
Glama
Sign In

md-doc

by com.md-doc.app
OverviewDiscussionsAdmin

file_upload_link

Para adjuntar archivos que están en disco (o de más de 5 MB, hasta 250 MB cada uno) sin pasar su contenido por la conversación: devuelve una URL de un solo uso, válida 15 minutos, y el comando curl para subirlos desde la terminal (hasta 10 archivos en la misma llamada, un -F por archivo). La URL es una credencial: no la muestres ni la guardes en notas o bitácoras. Si curl falla por un archivo no admitido, puedes reintentar con la misma URL; una vez usada con éxito, pide otra. target: note (nota), issue, task (tarea recurrente) o expedient_line (registro/expediente: los adjuntos de un registro van en una de sus líneas de actuación; búscala con expedient_lines_list o créala con expedient_line_add). id: el de ese elemento.

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": {
      "target": "<target>",
      "id": "<id>"
    },
    "name": "file_upload_link"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesID de la nota, issue, tarea recurrente o línea de registro
targetYesDónde está el adjunto

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral load and does so: it discloses one-time use, a 15-minute expiry, per-file and per-call size/count limits, the exact curl -F pattern, and retry semantics after partial failure. It also flags a security constraint — the URL is a credential and must not be displayed or stored in notes or logs.

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?

One dense paragraph, front-loaded with the purpose and limits before the security warning and target semantics. Nearly every clause carries actionable information, though the run-on structure with parentheticals makes it harder to scan than a short bulleted breakdown would be.

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

Completeness5/5

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

For a two-parameter tool with no output schema, the description covers what the call returns (one-use URL plus curl command), the limits, the security handling, failure/retry behavior, and how to resolve the expedient_line case. Nothing an agent needs in order to invoke it correctly appears missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning: it enumerates what each target value refers to (note, issue, recurring task, expedient line) and explains that a record's attachments belong to one of its action lines, which must be located or created first. The id parameter is tied to 'the ID of that element'.

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: it returns a one-use URL (valid 15 minutes) plus a curl command to upload files that live on disk, without passing their content through the conversation. That scope ('on disk', 'over 5 MB, up to 250 MB', 'up to 10 files per call') implicitly separates it from a content-upload sibling, but no alternative is named explicitly.

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?

The opening clause establishes the when-to-use condition (files already on disk or larger than 5 MB) and the retry rule is explicit: if curl fails on a rejected file, reuse the same URL; once it succeeds, request a new one. It also routes the agent to expedient_lines_list / expedient_line_add when the target is an expedient_line. No explicit 'when not to use' or named counterpart tool is given.

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

All md-doc toolsInspect
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