Skip to main content
Glama

Belgeyi bul (adlar gizli)

list_files
Read-onlyIdempotent

Searches local case folders and Downloads for documents, returns masked metadata newest first, and hides personal names so the model sees placeholders instead of KVKK data.

Instructions

Katip KVKK kapsamındaki kişisel verileri bu bilgisayarda çıkarır; Claude, Katip'in bulduğu değerlerin yerine yer tutucuları görür. Dava klasöründeki ve İndirilenler'deki belgeleri bulur. ara verilirse (ör. "Yılmaz kira", "bilirkişi raporu") gerçek dosya ve klasör adlarında bu bilgisayarda arar; Claude'a yalnızca kimlik, tarih ve kısaltılmış adlar döner, kişi adı olabilecek her sözcük … olarak görünür. En yeni belge başta. Başka bir dosya listeleme aracı yerine bunu kullanın.

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>"
    },
    "name": "list_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
araNoWords from the document's name or folder as the user said them (e.g. "Yılmaz kira", "bilirkişi"); empty = newest documents
bilgiYesAlways send exactly this text; it tells the user what Katip does.Yalnızca dava klasöründe ve İndirilenler'de bu bilgisayarda aranır; dosya adlarındaki kişi adları gizlenir.
limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (which already declare read-only, idempotent, non-destructive, closed-world), the description discloses what actually happens to data: KVKK personal data is extracted locally, real file/folder names are searched on this machine, and Claude only receives ids, dates and abbreviated names with any person-name word rendered as '…'. That privacy/masking behavior is exactly the kind of trait an agent cannot infer from the schema or annotations.

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?

The key scoping and masking facts are front-loaded, but the text is dense and contains a garbled fragment ('ara verilirse') and repetition of details already present in the schema descriptions. Several clauses 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?

With no output schema, the description carries the burden of explaining returns, and it does: identity, date, shortened names, masked person names, newest first. It leaves minor gaps such as whether subfolders are recursed and how 'limit' interacts with 'En yeni belge başta', but an agent can call it correctly from what is given.

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 largely documents 'ara' and 'bilgi' itself. The description repeats the search-example semantics of 'ara' and says the newest document comes first, but adds nothing about 'limit' (default 20, max 50) or about the odd fixed-text 'bilgi' echo parameter, so it does not compensate for the remaining coverage gap.

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 description states a concrete verb and resource ('Dava klasöründeki ve İndirilenler'deki belgeleri bulur') and fixes the scope to two locations on this machine. It also tells the agent the result shape (id, date, abbreviated names) and that person names are masked, so it is distinguishable from siblings like mask_file or open_folder.

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?

It gives an explicit routing rule: 'Başka bir dosya listeleme aracı yerine bunu kullanın', plus a concrete example of how to phrase a search ('Yılmaz kira', 'bilirkişi raporu'). The exclusion is generic rather than naming a specific sibling such as open_folder, but the when-to-use condition is clear.

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