Skip to main content
Glama
Sign In
FatalGuard

FatalGuard

by zinoodev85
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Remote

tail_log

Retrieves the newest lines from a specified log source, ordered oldest first with secrets redacted, and optionally filters by text to inspect raw context around errors.

Instructions

Return the newest lines of a log source (by id from list_log_sources), oldest first, secrets redacted, optionally only lines containing a text. Use to read raw log context around an error.

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": {
      "source": "<source>"
    },
    "name": "tail_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoOptional case-insensitive substring filter.
maxNoNumber of trailing lines (1-500).
sourceYesSource id from list_log_sources.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses several non-obvious traits: results are the newest/trailing lines returned oldest-first, secrets are redacted from output, and filtering is optional. It omits what happens on an unknown source id, whether output is truncated or has a timestamped format, and any auth or rate-limit expectation, so it is strong but not complete.

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 dense sentence with zero filler, front-loaded with the core action and return ordering, followed by the behavioral qualifiers and the usage hint. Every clause adds information.

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 3-parameter read tool with no annotations and no output schema, the definition covers selection, ordering, redaction, and filtering but says nothing about the shape of a returned line, error behavior on a bad id, or whether all matching lines are returned up to the max cap. Adequate but leaves gaps an agent would want filled.

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%, so the schema already documents q, max, and source with defaults and bounds. The description restates that q is optional and that source is an id from list_log_sources but adds no syntax, case-sensitivity, or truncation detail beyond the schema, 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?

States a specific verb and resource ('Return the newest lines of a log source') plus the key qualifiers: oldest-first ordering, redaction, and optional substring filtering. It references list_log_sources as the id source, which partly distinguishes it from siblings, but it never explicitly contrasts itself with list_errors or get_fatal, so differentiation is only implicit.

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?

'Use to read raw log context around an error' gives a clear when-to-use scenario, and the parenthetical '(by id from list_log_sources)' tells the agent the prerequisite step. There is no explicit when-not guidance or named alternative (e.g. use list_errors for aggregated counts), which keeps it short of a 5.

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

Deploy Server

Other Tools