Skip to main content
Glama

adb_find

Search Android device files by name or glob pattern using find, with capped results and truncation reporting to keep output bounded.

Instructions

Search for files on the device by name or pattern. Uses the find command with glob matching. Results are capped at maxResults to prevent unbounded output. Reports whether results were truncated.

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": {
      "name": "<name>"
    },
    "name": "adb_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesFilename pattern (glob: *.apk, config.*, *test*)
rootNoUse root shell for system paths
typeNoFilter by type: file, directory, or anyany
deviceNoDevice serial
maxDepthNoMaximum directory depth to search (1-50, default 10)
maxResultsNoMaximum results to return (1-10000, default 500)
searchPathNoStarting directory for search/sdcard
result_handleNoOptional. If provided, store this tool's result under `result://<tool>/<name>` for retrieval after compaction. Name must be 1-32 chars, [a-zA-Z0-9_-]. Existing handles with the same tool+name are overwritten. Use adb_result_list to see active handles, adb_result_get or the MCP Resource URI to retrieve.
result_handle_ttlNoOptional. TTL in seconds for the result handle (60 to 604800). Default 43200 (12 hours). Ignored if result_handle is not provided.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.6
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed3 schema fields changedv1.1.3
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / result_handle
      Added value: +{
      +  "description": "Optional. If provided, store this tool's result under `result://<tool>/<name>` for retrieval after compaction. Name must be 1-32 chars, [a-zA-Z0-9_-]. Existing handles with the same tool+name are overwritten. Use adb_result_list to see active handles, adb_result_get or the MCP Resource URI to retrieve.",
      +  "maxLength": 32,
      +  "minLength": 1,
      +  "pattern": "^[a-zA-Z0-9_-]+$",
      +  "type": "string"
      +}
    • addedInput schema / properties / result_handle_ttl
      Added value: +{
      +  "description": "Optional. TTL in seconds for the result handle (60 to 604800). Default 43200 (12 hours). Ignored if result_handle is not provided.",
      +  "maximum": 604800,
      +  "minimum": 60,
      +  "type": "integer"
      +}
  3. First observedv1.1.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does deliver real value: it discloses the maxResults cap and that truncation is reported, which tells the agent output can be incomplete. It omits other behavioral facts that matter here — that root may be needed for system paths, that the search is scoped to searchPath (default /sdcard) and maxDepth, and roughly what a result entry looks like.

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?

Four short sentences, each carrying distinct information (purpose, mechanism, output bound, truncation reporting), with purpose front-loaded and zero filler.

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 9-parameter, no-output-schema, no-annotation tool, the description covers the essentials an agent needs to call it correctly: the glob matching model and the bounded-output contract. Remaining gaps — default search scope, depth limiting, root requirement — are all documented in the schema, so completeness is only marginally short.

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 100%, so the baseline is 3. The description reinforces two parameters (maxResults cap and its truncation consequence) and the glob semantics of 'name', but adds nothing for root, device, maxDepth, searchPath, or the result_handle pair beyond what the schema already documents.

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 ('Search for files on the device by name or pattern') and adds the implementation basis ('find command with glob matching'), which distinguishes it from content searches and simple listings. It never names the closest siblings (adb_ls, adb_grep, adb_file_stat, adb_ui_find), so differentiation must be inferred from the verb.

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?

The glob-pattern framing implies when to reach for this tool (name-pattern lookups across a tree), but there is no explicit when-to-use/when-not guidance and no mention of adb_ls for single-directory listing or adb_grep for contents. An agent must infer the boundary from the sibling names alone.

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

Deploy Server

Other Tools