Skip to main content
Glama

flipper_navigate

Send button-press sequences to navigate Flipper Zero menus and optionally capture the resulting screen in one call.

Instructions

Send a sequence of button presses to navigate menus. keys is comma- or space-separated, e.g. 'down,down,ok' or 'back back up ok'. Valid keys: up/down/left/right/ok/back; append ':long' for a long press, e.g. 'ok:long'. A short pause runs between presses. With screenshot=True the screen after the last press is returned too, so one call both acts and shows the result.

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": {
      "keys": "<keys>"
    },
    "name": "flipper_navigate"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysYes
delay_msNo
screenshotNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and idempotentHint=false, so the agent knows this mutates device state. The description adds genuine value beyond that: a pause runs between presses, presses are applied in order, and with screenshot=True the post-sequence screen is returned. It does not say how invalid keys or unreachable menus are reported, which matters for a non-idempotent navigation call.

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?

Four tight sentences, front-loaded with what the tool does, then the key grammar, then the screenshot payoff. No filler, though the two syntax examples ('comma- or space-separated') could be merged into one clause.

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 three-parameter mutation tool with annotations covering the safety profile and no output schema, the description supplies what is needed to invoke correctly: key grammar, ordering, and screenshot return behavior. The remaining gaps are the undocumented delay_ms parameter and the absence of any failure-mode note.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden. It fully documents the required 'keys' parameter: separator variants, the complete valid-key set (up/down/left/right/ok/back), and the ':long' suffix grammar. It also explains 'screenshot'. However 'delay_ms' is never named, leaving the third parameter's meaning inferable only from 'a short pause runs between presses'.

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 concrete verb and resource: 'Send a sequence of button presses to navigate menus.' The word 'sequence' signals it is not a single-press tool, though it never names or contrasts a sibling such as flipper_press or flipper_screenshot.

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?

Gives concrete usage context via worked examples ('down,down,ok', 'back back up ok') and explains the screenshot=True case as 'one call both acts and shows the result', which implicitly routes the agent away from a separate screenshot call. It stops short of naming when NOT to use it or naming the alternative tool.

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