Skip to main content
Glama

pilot_chat_wait

Read-onlyIdempotent

Poll a chat response region until its text changes and stabilizes, optionally waiting for specific content. Use a prior baseline to avoid missing quick responses.

Instructions

Poll a unique accessible response region until text changes (by default) and becomes stable, optionally containing a string. Stable does not mean generation is complete. Supply baseline from your last read to avoid missing fast responses.

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": {
      "app": "<app>",
      "region": "<region>",
      "require_change": "<require_change>",
      "stable_ms": "<stable_ms>",
      "timeout_ms": "<timeout_ms>"
    },
    "name": "pilot_chat_wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYes
regionYes
baselineNo
containsNo
stable_msYes
window_idNo
timeout_msYes
require_changeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/open-world, yet the description adds a genuinely useful caveat: 'Stable does not mean generation is complete,' which corrects a likely agent misconception. It stops short of describing timeout behavior (what happens at timeout_ms) or the failure mode when the region is absent.

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?

Three tight sentences, front-loaded with the core operation and the stability semantics before the baseline tip. Slightly dense jargon ('unique accessible response region') but no wasted words.

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, nested-object polling tool with no output schema, the description leaves meaningful gaps: the return shape, what a timeout yields, and the meaning of stable_ms/timeout_ms are never addressed.

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 carry the load. It clarifies require_change ('by default'), contains ('optionally containing a string'), baseline (from last read) and region (accessible response region), but says nothing about app, window_id, stable_ms, or timeout_ms, leaving half the parameters undocumented.

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+resource ('Poll a unique accessible response region') plus the stopping conditions (text changes and becomes stable). It doesn't name a sibling like pilot_chat_read or desktop_wait to contrast against, so differentiation is inferred rather than stated.

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?

Implies the polling use case and gives one operational guideline ('Supply baseline from your last read to avoid missing fast responses'), but never says when to choose this over pilot_chat_read or desktop_wait, nor when not to use it.

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