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

Host Process & Sub-Agent Governor

by jasonroject

host_exec_logs

Read captured stdout, stderr, and system logs from a background host process, with secret redaction, to inspect recent output or filter by timestamp.

Instructions

Read captured stdout, stderr, and system logs from a background host process (with secret redaction).

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>"
    },
    "name": "host_exec_logs"
  }
}

Input Schema

NameRequiredDescriptionDefault
tailNoNumber of recent log lines to retrieve (default: 100).
processIdYesProcess ID to inspect logs for.
sinceTimestampNoISO timestamp to filter logs after.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it delivers one genuinely useful trait: secrets are redacted from the returned logs. It also implies logs are buffered/captured rather than streamed live. It says nothing about permissions, retention limits, or whether the read has side effects, and 'Read' only implicitly signals read-only.

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?

One front-loaded sentence that identifies the action, the three log sources, and the redaction caveat with zero filler.

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?

For a simple three-parameter read tool, the definition covers what is read and the redaction behavior. Because there is no output schema, it could have said more about the shape of returned log entries (fields, interleaving of stdout/stderr), which is the one remaining gap.

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%, with tail, processId, and sinceTimestamp each documented including the default of 100. The description adds no semantics beyond the schema except the redaction note, so baseline 3 applies.

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?

Specific verb-resource pair: reading captured stdout, stderr, and system logs from a background host process. That clearly separates it from host_exec_status or host_exec_start by the artifact returned, though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance and no comparison to host_exec_status, which is the most likely competing tool for inspecting a process. The agent must infer that this is for retrieving log output after a process is started.

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