Skip to main content
Glama

Search the logs of many deployments at once

edgegap_search_deployment_logs
Read-only

Search container and crash logs of running deployments for a pattern, grouped by error with counts and source deployments. Finds exceptions, fatal signals, and OOM kills across up to 100 deployments.

Instructions

Search the container and crash logs of running deployments of an application (and version) for a pattern, and group the matching lines by error, with counts and which deployments printed them: "every crash in version 1.4.2 since yesterday, grouped by error". Without a pattern it looks for errors, exceptions, fatal signals and out-of-memory kills. Also counts crash exit codes. Logs only exist while a deployment runs (or in Endpoint Storage), so stopped deployments are not searched. Searches up to 100 deployments per call, newest first. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "edgegap_search_deployment_logs"
  }
}

Input Schema

NameRequiredDescriptionDefault
regexNoTreat pattern as a regular expression. Default false.
patternNoText to find, case-insensitive. Default: common error and crash words.
versionNoOnly this version (needs application).
max_groupsNoMost error groups to return, 1-50. Default 15.
applicationNoOnly this application. Default: all.
started_afterNoOnly deployments started after this ISO 8601 time, e.g. "2026-11-12T00:00:00Z" for the last day.
max_deploymentsNoHow many to search, 1-100. Default 30.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.19.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description's closing 'Read-only' merely restates that. It does add real behavior beyond the annotations: the default error-word search when no pattern is supplied, crash exit-code counting, newest-first ordering, and a 100-deployment cap per call. Those operational limits are useful, but return format and result-size behavior are only loosely sketched.

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?

Front-loads the core action and the grouped-by-error output before the qualification about stopped deployments. It is dense and the long multi-clause opening sentence plus the illustrative quote cost some readability, but almost every clause carries information.

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 7 optional parameters, no output schema, and annotations covering only safety, the description does the necessary work: it explains the default pattern behavior, the grouping/counting result, the running-only log constraint, and the per-call deployment cap. Pagination and the exact response envelope remain unstated, which is the main residual 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 coverage is 100%, so every parameter is already documented, making 3 the baseline. The description elaborates one default meaningfully ('Without a pattern it looks for errors, exceptions, fatal signals and out-of-memory kills' vs. the schema's terser 'common error and crash words') and frames application/version together, but adds nothing on regex, max_groups, or max_deployments beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and resource (container and crash logs) with explicit scope: 'many deployments of an application (and version)', which cleanly separates it from the single-deployment sibling edgegap_get_deployment_logs. The output shape (grouped by error, with counts and source deployments) is stated up front.

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 a concrete usage framing via the quoted example ('every crash in version 1.4.2 since yesterday, grouped by error') and states a hard precondition: logs only exist while a deployment runs or in Endpoint Storage, so stopped deployments are not searched. It does not explicitly point to the single-deployment log tool as the alternative for one deployment, which keeps it below a 5.

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