Skip to main content
Glama
synology-mcp
by r03eRt

Drive: search

drive_search
Read-only

Search Synology Drive files and folders by keyword, type, location, owner, size, or modified date to locate documents on your NAS.

Instructions

Search Synology Drive by name/content keyword, type, location, labels, owner, size or date. Newly added files can take a few seconds to be indexed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "drive_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoDefault 1000
ownerNo
offsetNo
keywordNo
locationNoany (default), mydrive, team_folders, shared_with_me, shared_with_others, starred, or a Drive path
max_sizeNoBytes
min_sizeNoBytes
file_typeNo
label_idsNoLabel IDs from drive_list_labels
modified_afterNoISO date
content_snippetNoInclude a text snippet of the match
modified_beforeNoISO date

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.0

TDQS

A3.5/5.0
Behavior3/5

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

The indexing caveat ('newly added files can take a few seconds to be indexed') is genuine operational context not present in the readOnlyHint/openWorldHint annotations, and it usefully explains stale-looking results. Beyond that the description says nothing about result ordering, pagination interaction between limit/offset, or total counts. With annotations already covering the safety profile, this is a 3.

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?

Two short sentences, capability stated first and the caveat second – well front-loaded with no filler. It is arguably under-specified rather than verbose, but nothing in it is wasted.

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 read-only search tool with twelve optional parameters and no output schema, the description covers what the tool searches over and flags the one behavior an agent would otherwise misread (indexing lag). Pagination and snippet-return behavior are left to the schema, which is an acceptable trade-off but keeps it short of fully complete.

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?

Description coverage is 67%, and the description's filter list (keyword, type, location, labels, owner, size, date) maps onto most of the twelve parameters, adding modest orientation value. It omits limit/offset paging semantics and content_snippet entirely, and adds no format detail (e.g. byte units, ISO date format) beyond what the schema already states.

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 (search) and resource (Synology Drive) and enumerates the filterable dimensions: name/content keyword, type, location, labels, owner, size, date. It does not name or contrast any sibling such as drive_list, drive_recent, or drive_starred, so the agent must infer the boundary itself.

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?

Usage is implied by the enumerated filter axes – an agent can reason that this is the tool for filtered retrieval rather than listing. However, there is no explicit when-to-use/when-not guidance and no pointer to alternatives like drive_list for plain enumeration or drive_starred for starred-only retrieval.

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