Skip to main content
Glama

pilot_chat_write

Writes and verifies exact multiline text in a unique chat composer, preserving drafts unless replacement is requested; optionally sends once using a request ID to prevent replay.

Instructions

Write and verify exact multiline text in a unique accessible composer. Preserves an existing draft unless replace=true. Optional send clicks a fresh unique button once. request_id prevents replay across restarts when Rust is enabled; reuse it after uncertain delivery. Never sends Enter to a terminal.

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>",
      "target": "<target>",
      "text": "<text>",
      "replace": "<replace>",
      "request_id": "<request_id>"
    },
    "name": "pilot_chat_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYes
sendNo
textYes
targetYes
replaceYes
window_idNo
request_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare mutation, open-world and non-idempotent, so the description carries real added weight: draft preservation, single click of a fresh button, replay protection via request_id, and the no-Enter safety rule. It slightly obscures the replay story with the conditional 'when Rust is enabled', and the request_id dedup sits in mild tension with idempotentHint=false, though not enough to be a contradiction.

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?

Short and front-loaded: the core write/verify action comes first, then draft behavior, then send, then replay semantics, then the safety rule. Some phrasing is telegraphic ('unique accessible composer', 'fresh unique button once') and the 'when Rust is enabled' clause is implementation leakage an agent cannot act on.

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

Completeness2/5

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

For a 7-parameter, nested-object, mutating, open-world tool with no output schema and zero schema descriptions, the description leaves major gaps: how target uniqueness is determined, what app/window_id do, what 'verify' returns, and failure behavior. It covers the interesting edge cases but not enough of the surface for reliable invocation.

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 description coverage is 0%, so the description must carry parameter meaning and it only partly does: replace, send and request_id are explained in behavioral terms. app, target, window_id and text are not described at all, and the nested role/name contract on target and send is left entirely to the schema.

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 and resource: writes and verifies exact multiline text into a uniquely accessible composer, which clearly separates it from pilot_chat_read and pilot_chat_wait. It never names a sibling explicitly, so it stops short of a 5, but the action and target are unambiguous.

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?

Gives concrete conditions inline: preserve the existing draft unless replace=true, opt into sending via the send object, and reuse request_id after uncertain delivery. It also states a hard boundary (never sends Enter to a terminal) but does not name alternatives or say when to use pilot_chat_read/pilot_chat_wait instead.

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