Skip to main content
Glama

Gerçek adlarla dosyaya kaydet (bu bilgisayarda)

restore_to_file

Replaces placeholders such as [AD SOYAD-1] with locally stored real values and writes the result to a new local file, returning only the file path and count.

Instructions

Metindeki [AD SOYAD-1] gibi yer tutucuları bu bilgisayarda saklanan gerçek değerlerle değiştirir ve sonucu yeni bir yerel dosyaya kaydeder. Claude'a yalnızca dosya yolu ve sayı döner, gerçek değerler asla dönmez.

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": {
      "bilgi": "<bilgi>",
      "text": "<text>",
      "output_path": "<output_path>"
    },
    "name": "restore_to_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
bilgiYesAlways send exactly this text; it tells the user what Katip does.Gerçek adlar yalnızca bu bilgisayarda, kaynak belgenin yanına yeni bir dosya olarak yazılır; Claude'a yalnızca dosya adı döner. Göndermeden önce son metni okuyun.
matterNoMatter (dosya) label; files of the same case share placeholders. Use a neutral label such as a file number, not a client name.default
output_pathYesFile name, saved next to the source document: .docx, .txt or .md (e.g. cevap-dilekcesi.docx)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare the generic safety profile (not read-only, not destructive, not idempotent, not open-world). Beyond that, the description discloses the key behavioral trait: real values are restored only inside the generated file and are never returned to Claude, and only a path and a count come back. It does not say what happens if output_path already exists, though the non-idempotent annotation hints at overwrite risk.

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, both front-loaded with substance: the first gives the transformation and destination, the second gives the return contract. No filler, no repetition of the title.

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 correctly explains the return shape (path and count), which is the most important thing an agent needs since it cannot read the real values back. The combination of annotations, schema, and description covers a 4-parameter local-write tool well; only overwrite and failure behavior remain unstated.

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 75%, so the schema largely carries parameter meaning: matter, output_path, and the always-send bilgi constant are all documented there, along with the supported extensions. The description adds no further parameter-level detail beyond restating that placeholders live in the text. Baseline 3 is appropriate.

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?

The description states a concrete verb and resource: it replaces placeholders such as [AD SOYAD-1] with real values stored locally and writes the result to a new local file. It also clarifies the shape of what comes back (file path and count only, never the real values), which implicitly separates it from a counterpart that returns real values. Its only gap is that it never addresses its sibling restore or mask tool (write_masked_copy, mask_file) by name.

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

Usage Guidelines3/5

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

When to use the tool is only implied: you use it when you want the final text with real names written to disk. There is no explicit statement of alternatives (for example, that you should write a masked copy instead when sending a document out) and no mention of prerequisites. Adequate for a simple two-step workflow, but it leaves the routing to the reader.

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