Skip to main content
Glama
newsbubbles

ismail: agent DAW (MCP server)

Phone Say

phone_say

Send captions and optional spoken replies to a phone, pin summaries, vibrate, and set priority so users receive timely, prompted-only updates.

Instructions

A caption on the phone. speak=True also says it into the stream (Kokoro, the music ducked under it), so they hear it in their pocket: only to answer something they said, never unprompted. pin=True keeps it at the top (a "since you left" summary). buzz=True vibrates the phone if the page is open. priority: 'needs you' (sorts first and lights the corner key in the accent colour), 'normal' (the default) or 'low' (sorts last). Refused: text naming a place or personal detail from the local private terms (rephrase it), and a yes/no question ("should I merge ...?") that a standing grant already answers (act on the grant and say what you did; override_grant='' asks anyway and logs the reason). phone.md, "Nothing personal on the page" and "Don't ask for what is granted".

Input Schema

NameRequiredDescriptionDefault
pinNo
buzzNo
textYes
speakNo
voiceNo
senderNo
priorityNo
override_grantNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and discloses meaningful effects: speak plays audio with music ducking, pin keeps the caption at top, buzz vibrates if the page is open, priority affects sorting and the corner key, and refusals/override logging are explained. It omits auth requirements and error handling beyond refusals, but covers core behavior well.

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?

Every sentence conveys relevant behavior or a constraint, and the purpose is front-loaded. The dense run-on formatting makes it harder to scan, but there is little wasted content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with no annotations, the description covers most operational rules and refusal behavior, and an output schema exists for return values. However, it leaves voice and sender unexplained, so it is not fully complete for the parameter surface.

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 0%, so the description must explain all 8 parameters. It meaningfully covers speak, pin, buzz, priority, and override_grant, but leaves text, voice, and sender undocumented, making the parameter semantics incomplete.

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 opens with "A caption on the phone" and then details speech, pinning, buzzing, and priority, making it clear this posts a caption/message to the phone. It does not explicitly name sibling tools like phone_ask or phone_buzz, so differentiation relies on usage constraints rather than direct comparison.

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 a strong when-to-use rule ("only to answer something they said, never unprompted") and explicit refusal cases with alternative actions (act on a standing grant instead of asking). It does not name specific sibling tools to use for other cases, but the contextual guidance is clear.

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