Skip to main content
Glama

wait

Read-only

Pauses automation until the IBM i host is ready for input, optionally matching specific screen text, so commands and sign-on steps finish before continuing.

Instructions

Wait until the host is waiting for input (and optionally for some text), e.g. after a long-running command or while the user signs on.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNowait until this text is on screen
sessionNosession name; lets you run several side by sidemain
timeoutNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

The readOnlyHint annotation already establishes that this is a safe, non-mutating call, so the description's main added value is that the call blocks on a host-state condition rather than returning immediately. It does not disclose what happens when the wait fails or expires — whether the tool returns an error, a partial result, or an empty payload — which is the key behavioral question for a blocking tool.

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?

A single well-formed sentence with the core blocking behavior front-loaded and the optional text condition following. Nothing is wasted, though the parenthetical example clause carries more weight than the omitted timeout semantics.

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

Completeness5/5

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

Wait-what an agent needs in order to call it correctly is present: the condition it blocks on, the optional text filter, the session selector, and the safety profile via annotations. The output schema covers return values, and no required parameters exist, so a missing timeout description is a detail rather than an incompleteness.

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 67%; text and session are documented in the schema, and the description's 'optionally for some text' merely echoes the text parameter. The timeout parameter has no description in either the schema or the description, leaving its unit and expiry semantics entirely undocumented, so the description does not compensate for the coverage gap.

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 states a specific verb and a precise condition: 'wait until the host is waiting for input (and optionally for some text).' That is far more than a restatement of the name 'wait' and tells the agent exactly what state the tool blocks on. It does not, however, differentiate itself from siblings such as 'get_screen' or 'get_session_log', which an agent might mistakenly use for polling.

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?

Usage is conveyed only through examples ('after a long-running command or while the user signs on'), which implies when to call it but gives no explicit exclusions or named alternatives for polling. There is no statement about when not to use it, or how it relates to the sibling inspection tools.

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