Skip to main content
Glama

Dateien schreiben

fs_write

Schreibt eine oder mehrere Textdateien in den Workspace. Alle Dateien eines Aufrufs werden zusammen zu einer Version; schlägt eine fehl, wird keine geschrieben. Bilder und andere Binärdateien gehen nicht durch den Chat: upload_link gibt dem Kunden die Adresse, unter der er sie hochlädt; asset_add_from_url holt eine Datei, die schon im Web liegt. Was hier geschrieben wird, ist der AUSGELIEFERTE Stand: zur Laufzeit read-only, und bei jedem Publish ersetzt. Der Datenbereich einer Website mit PHP (/var/www/storage) gehört NICHT dazu – dort schreibt nur ihr PHP, und hochgeladen wird dorthin im Portal. Keine Zugangsdaten in eine Datei hier: sie stünden im veröffentlichten Stand und in jeder Version.

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": {
      "website": "<website>",
      "files": "<files>"
    },
    "name": "fs_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYes
messageNoWas diese Änderung bewirkt, für die Versionsliste
websiteYesKennung oder Name der Website. Reicht der Zugang ueber mehrere Organisationen und gibt es die Kennung mehrfach, «organisation/website» schreiben.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing atomic all-or-nothing semantics per call ("schlägt eine fehl, wird keine geschrieben"), the fact that one call becomes one version, and that the written state is the delivered state — read-only at runtime and replaced on every publish. The security warning about credentials leaking into published output and history is exactly the kind of context annotations cannot carry. It stops short of 5 because it never says whether new files and parent directories are created, nor what the call returns.

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 core action, then alternatives, then the delivery/versioning model, then the exclusion and the security warning — a sensible order. It is dense and every sentence carries information, though the delivery-model and credentials sentences could be tightened 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 mutation tool with no output schema, it covers atomicity, versioning, the read-only delivered state, the storage exclusion and the secrets hazard — far more than most write tools. The remaining gap is create-vs-overwrite and directory creation behaviour, which an agent needs in order to avoid a failed call on a new path.

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%, so the schema already documents path, content, message and website in detail, including the relative-path convention and the organisation/website disambiguation. The description adds only the implicit constraint that content is text and that a call is scoped to one workspace, without elaborating on any individual parameter. Baseline 3 is appropriate.

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?

The first sentence names a specific verb and resource ("Schreibt eine oder mehrere Textdateien in den Workspace") and immediately narrows the scope to text files. It also names the sibling tools that handle the cases this tool does not cover (upload_link, asset_add_from_url), so an agent can route correctly without opening any schema.

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

Usage Guidelines5/5

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

Explicit when-to-use and when-not-to-use: binary files go through upload_link or asset_add_from_url, and the PHP data area /var/www/storage is explicitly out of scope with the note that uploads there happen via the portal. It also states a hard prohibition (no credentials in written files), which is a usage constraint rather than just a capability statement.

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