Skip to main content
Glama
Sign In

Sats4AI - Bitcoin-Powered AI Tools

by io.github.cnghockey
OverviewDiscussionsAdmin

poll_voice_bridge

Fetch new transcript events from an open Voice Bridge call since the last cursor. Returns partial + final transcripts + system events. Pass waitMs (e.g. 20000) to hold the call until the callee has FINISHED TALKING (a final transcript, then 0.7 s of silence) or the call changes state, then get everything at once: no polling timer, and you do not answer in the middle of their sentence. Without waitMs, poll in a loop (~500ms-1s) and decide yourself when they are done. No additional payment.

Input Schema

NameRequiredDescriptionDefault
cursorNoLast seq number seen (default 0 = start from beginning)
waitMsNoOptional. Hold the call up to this many milliseconds (max 25000) until the callee has finished talking: a FINAL transcript has arrived and nothing new for quietMs, or a system event arrives. Then everything since the cursor is returned at once. Partial transcripts alone do not end the wait. Default 0 = return immediately.
quietMsNoOptional, used with waitMs. How many milliseconds of silence after a final transcript count as 'finished talking' (0-5000, default 700). 0 = return at the first final transcript, even mid-sentence.
sessionIdYesSession ID from open_voice_bridge

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / quietMs
      Added value: +{
+  "description": "Optional, used with waitMs. How many milliseconds of silence after a final transcript count as 'finished talking' (0-5000, default 700). 0 = return at the first final transcript, even mid-sentence.",
+  "type": "number"
+}
    • addedInput schema / properties / waitMs
      Added value: +{
+  "description": "Optional. Hold the call up to this many milliseconds (max 25000) until the callee has finished talking: a FINAL transcript has arrived and nothing new for quietMs, or a system event arrives. Then everything since the cursor is returned at once. Partial transcripts alone do not end the wait. Default 0 = return immediately.",
+  "type": "number"
+}
  2. First observed

TDQS

A4.5/5.0
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 does substantial work: it discloses the returned event types, the long-poll ceiling (max 25000), the definition of 'finished talking' (final transcript + quiet period or state change), that partials alone do not end the wait, and that there is no additional charge. It stops short of covering session-end behavior or error conditions, which keeps it from a 5.

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?

Front-loaded with the core action and return payload, then moves to the waitMs decision. It is slightly dense and repeats the wait/poll tradeoff that the schema also encodes, but no sentence is 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 4-parameter, no-annotation, no-output-schema tool this covers the essentials: what comes back, how to paginate with cursor, and how to block versus poll. Only edge cases (session termination, error surfaces) are left unspecified.

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 coverage is 100%, so the baseline is 3; the description goes beyond by explaining the practical intent of waitMs (e.g. 20000) and the polling cadence to use when it is omitted. It reinforces cursor semantics as 'since the last cursor' in context of a polling loop rather than merely restating field types.

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?

States a specific verb and resource ('Fetch new transcript events from an open Voice Bridge call since the last cursor') and immediately enumerates what is returned (partial transcripts, final transcripts, system events). This clearly separates it from siblings like open_voice_bridge, voice_bridge_say and end_voice_bridge, which are named or implied elsewhere in the definition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit either/or: use waitMs to long-poll until the callee finishes speaking, or poll in a loop at ~500ms-1s and decide completion yourself. It even explains the motivation ('you do not answer in the middle of their sentence') and notes no extra payment, so the agent can choose a strategy without inference.

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

All Sats4AI - Bitcoin-Powered AI Tools toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources