Skip to main content
Glama

press

Destructive

Sends a 5250 key to the host after optional field fills and returns the resulting screen, enabling menu navigation, data entry, and automated testing.

Instructions

Send a key to the host (after optional fills) and return the screen the host answers with. Reset only clears an operator error locally.

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": {
      "key": "<key>"
    },
    "name": "press"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesEnter, F1-F24, PageUp, PageDown, Help, Clear, Print, SysReq, Attn, Reset
cursorNoput the cursor here first: "row,col", "#index" or a label (for F4 prompts, cursor-sensitive options, help)
expectNotext that must be on screen, or "row:text"
valuesNofields to fill first (same as fill)
sessionNosession name; lets you run several side by sidemain
timeoutNo
wait_forNokeep waiting until this text appears
screen_idNoscreen_id from your last read; refused if the screen changed

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare non-read-only, destructive, open-world behavior, and the description is consistent with that (it mutates host state). It adds real context beyond the annotations with the caveat that Reset only clears an operator error locally rather than affecting the host, but it says nothing about blocking/timeout semantics or what a refused call looks like.

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?

Two tight sentences with the core action front-loaded and no filler. The Reset clause is niche but is the only place the destructive scope nuance appears, so it earns its place.

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?

With an output schema present and 88% schema description coverage across 8 parameters, the description does not need to restate return values or field semantics. What is missing is a note on call-blocking behavior across expect/wait_for/timeout, but that is a modest gap given how rich the structured data is.

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 88%, so the input schema already documents key, cursor, expect, values, session, timeout, wait_for, and screen_id thoroughly. The description only echoes the fills behavior already captured by the 'values' parameter description, adding no new parameter meaning, which is the baseline-3 case.

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 gives a concrete verb and resource — 'Send a key to the host' — plus the response contract ('return the screen the host answers with'). The clause 'after optional fills' implicitly separates it from the sibling fill tool, and the Reset remark pins down a special key behavior, though it never names an alternative outright.

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?

'after optional fills' hints at the intended fill-then-press workflow rather than two separate calls, but there is no explicit statement of when to prefer this tool over keys, fill, or wait. Guidance is implied rather than stated.

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