Skip to main content
Glama

Save a file

add_file

Saves a file on the project from this AI tool, under this person's name: a PDF, a picture, a Word file, slides, a spreadsheet, a ZIP, or text over 1 MB. Takes the file's path on the project, plus one of two things: its size and SHA-256, which returns a command that sends the file, or the whole of a file up to 750 KB in base64, which saves it at once. With only the path, it returns how to send the file and the project's Files link. With replace, the file becomes a new version of the one at that path.

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": {
      "path": "<path>"
    },
    "name": "add_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
didNoWhat the person did themselves in this work, in a few words they agree with: what they chose or decided, what they corrected, rewrote or wrote, what they checked and against what. Start with the verb, in the past tense, in their language: "Chose the three-step plan; fixed the March totals; rewrote the opening". Say nothing of what you did, what they did not do, how long it took, or a share of the work. Pass no did when their part was the request and the yes. Everyone who sees the change reads it, people outside the team included. At most 300 characters.
forNoWho this is for. "team" when any of it is for the team only: pay, rates or costs, a line the client should not read, personal data. Alcoven then keeps it from people who see only some folders until the person answers in Alcoven. "everyone" when all of it is fine for everyone who sees the folder.
pathYesWhere it goes, with its name: reports/q3.pdf.
readNoThe § addresses you read for this work, kept with asked. Alcoven adds what it saw you read on this project since you last wrote on it, going back two hours at most.
sizeNoThe file's size in bytes.
askedNoWhat the person asked for, in their own words, as they said it: their request only, never the rest of the conversation, and left out when they do not want it shared. It goes on the project with the change, so everyone who sees the change, and their AIs, see why it was made.
titleNoA title, when its name says too little.
sha256NoThe file's SHA-256, in hex.
for_whyNoWith "team": a few words saying what in it is for the team, like "our day rate for the bank". The person and the project's managers read them.
projectNoThe project's slug, from open_project, like acme. Not needed when a § address names the project, or when the person is on one project.
replaceNoTrue to keep this as a new version of the file at that path.
asked_fromNoWhere the request came from, when the person says so, in a few words: "Tuesday's call with the bank", "Ines's email".
content_base64NoThe whole file in base64, up to 750 KB.

Output Schema

NameRequiredDescriptionDefault
filesNo
addressNo
appliedYes
commandNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare it is a non-read-only, non-destructive, non-idempotent write. The description adds real behavioral context beyond that: two distinct execution paths with different effects (deferred command vs immediate save), a size threshold for each, what is returned when no payload is given, and that replace versions the existing file rather than overwriting it. It does not mention permissions or error conditions, keeping it short of a 5.

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?

Front-loaded with the action and the payload modes, and every sentence carries information about branching behavior. It is a dense single paragraph whose file-type enumeration ("a PDF, a picture, a Word file, slides, a spreadsheet, a ZIP") could be compressed without losing meaning.

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 13-parameter, multi-mode tool with an output schema and full schema descriptions, the description covers the branching logic an agent needs to pick a mode and understand return behavior. It omits any mention that the call also attaches change metadata (did, asked, for, read) to the project, which is a notable part of what the tool does.

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 baseline is 3, but the description adds semantics the schema cannot express: size and sha256 are only meaningful together as the deferred-upload path, content_base64 is the immediate path with a 750 KB ceiling, and replace changes the write from create to version. The remaining metadata parameters (did, asked, for, read) are left entirely to their schema descriptions.

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 ("Saves a file on the project") plus accepted file types and the attribution model ("under this person's name"). It is clearly distinguishable from generic document tools, though it never names the nearest sibling (add_document) to draw the boundary 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?

Gives explicit mode-selection rules: path+size+sha256 returns a send command, path+content_base64 (≤750 KB) saves immediately, path alone returns upload instructions and the Files link, and replace creates a new version. This is strong when-to-do-what guidance, but there is no guidance on when to prefer this tool over sibling tools like add_document.

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.

Resources