Skip to main content
Glama
Host Process & Sub-Agent Governor

Host Process & Sub-Agent Governor

by jasonroject

host_exec_input

Send stdin text or keystrokes to an active interactive background process, enabling agents to answer prompts and control running sessions.

Instructions

Send stdin text to an active interactive background process.

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": {
      "processId": "<processId>",
      "input": "<input>"
    },
    "name": "host_exec_input"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesText/keystrokes to send to stdin.
processIdYesProcess ID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it only says the write goes to stdin of an already-active session. It does not disclose whether a trailing newline/Enter is appended (critical for keystroke semantics), whether the call blocks awaiting output, what error surfaces if the process has exited, or that this mutates an existing session rather than starting anything.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with the action and the target constraint front-loaded and no wasted wording. Nothing in it is redundant or padded.

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 a two-parameter tool with a fully covered schema and no output schema, the description covers the essential action and precondition. It still leaves the agent guessing about return behavior (any echoed output or confirmation) and newline/keystroke handling, which matters for an interactive-stdin tool with zero annotation coverage.

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 100% and both parameters are documented ('Process ID' and 'Text/keystrokes to send to stdin'), so the schema does the semantic work. The description adds no format hints such as whether processId matches the ID returned by host_exec_start, which keeps it at the baseline.

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 ('Send stdin text') and target ('an active interactive background process'), which is enough to separate it from host_exec_start, host_exec_logs, host_exec_status and host_exec_stop, since those operate on process lifecycle or output rather than input. It never names a sibling explicitly, so the 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?

The phrase 'active interactive background process' implicitly conveys the precondition that a session must already exist and be interactive, which is useful routing context. However, there is no explicit statement of when to use this versus host_exec_start (for new processes) or host_exec_logs (for reading output), and no guidance on what to do if the target process is dead or non-interactive.

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