Skip to main content
Glama

defect_triage

Read-onlyIdempotent

Bug-triage advisor. POST one bug report (or a list) and get severity (critical/high/medium/low), category, whether it has repro steps, and what info is missing (no repro / no expected-vs-actual / no environment). For a list: priority ranking + likely-duplicate clusters. Deterministic, no LLM.

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": "defect_triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
reportNoOne bug report as free text.
reportsNoAlternative: up to 50 reports, ranked by priority. Wins over report.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / report / description
      Added value: +"One bug report as free text."
    • addedInput schema / properties / report / maxLength
      Added value: +20000
    • addedInput schema / properties / reports / description
      Added value: +"Alternative: up to 50 reports, ranked by priority. Wins over report."
    • addedInput schema / properties / reports / items / maxLength
      Added value: +20000
    • addedInput schema / properties / reports / maxItems
      Added value: +50
    • addedInput schema / properties / reports / minItems
      Added value: +1
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: 'Deterministic, no LLM' tells the agent results are reproducible and rule-based, and the enumerated output fields set expectations for what comes back. It omits anything on limits or failure handling, but the annotation coverage lowers the bar.

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?

Three dense sentences, front-loaded with the purpose and followed by the per-mode outputs; there is no filler or restatement of the title. The parenthetical field lists ('critical/high/medium/low', 'no repro / no expected-vs-actual / no environment') pack a lot of meaning into little space.

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

Completeness5/5

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

There is no output schema, so the description carries the return-value burden itself and does so fully: severity scale, category, repro detection, missing-info categories, and for batch mode ranking plus duplicate clusters. For a two-parameter, purely analytical tool, nothing an agent needs in order to call it correctly is missing.

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 the schema already documents both parameters, including the precedence rule ('Wins over report') and the 50-item cap. The description restates the single-vs-list choice without adding syntax, format, or validation detail, so it is at the baseline where the schema does the heavy lifting.

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 and resource ('Bug-triage advisor. POST one bug report... and get severity, category, repro steps, missing info') and enumerates the exact outputs, so the agent knows precisely what the tool produces. The 'advisory/analysis' nature distinguishes it from write-oriented siblings such as create_upload or send_feedback.

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 description gives clear mode selection guidance ('POST one bug report (or a list)', 'For a list: priority ranking + likely-duplicate clusters'), which tells the agent how to pick between the single and batch forms. However it never names an alternative sibling (e.g. ticket_lint) or states when NOT to use this tool, leaving cross-tool routing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.