Skip to main content
Glama

Triage issue end-to-end

triage_issue
Read-onlyIdempotent

Merges a bug report with similar issues, fix context, pipeline warnings, and blast radius into one structured packet. Provides prioritized recommended actions to guide review before fix dispatch.

Instructions

Read-only combined tool: merges report detail, the reporter thread, similar bugs (matched on the report summary), the fix context (paste-ready fix prompt, repro steps, root cause), the blast radius of the inventory action the report is filed against, and recent pipeline warnings into a single structured review packet. Returns the packet plus prioritised recommended_actions, partial_errors for any source that failed, and notes for any source that does not apply (e.g. no blast radius when the report is not anchored to an inventory action). Equivalent to a Sentry "Analyze with Seer" flow grounded in user-felt reports. Pass reportId to kick off review. Call this before dispatch_fix.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reportIdYesReport UUID to triage. (`report_id` is accepted too.)
projectIdNoProject UUID. Defaults to configured project. (`project_id` is accepted too.)
includeLogsNoInclude recent pipeline logs in triage packet (default: true). (`include_logs` is accepted too.)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesYesSources that do not apply to this report, and why
reportYesThe report (documented fields, no reporter identifiers), or the error reading it
statusYesWorkflow status, or unknown
categoryYesbug | slow | visual | confusing | other, or unknown
severityYescritical | high | medium | low, or unknown when the report could not be read
report_idYesThe triaged report UUID
fix_contextYesFix-context slice, as get_fix_context returns it
recent_logsYesRecent warn+ pipeline log entries for the project, or null
blast_radiusYesDownstream nodes of the inventory action the report is filed against, or null
similar_bugsYesUp to five nearest reports by summary, excluding this one; null when not searched
partial_errorsYesSources that failed, as "source: message"
triage_summaryYesOne-line summary
reporter_threadYesThe unified report timeline (comments, fixes, QA), or null
recommended_actionsYesWhat to do next, most important first

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed35 schema fields changedv0.1.12
    • addedInput schema / properties / includeLogs
      Added value: +{
      +  "description": "Include recent pipeline logs in triage packet (default: true). (`include_logs` is accepted too.)",
      +  "type": "boolean"
      +}
    • removedInput schema / properties / include_logs
      Removed value: -{
      -  "description": "Include recent pipeline logs in triage packet (default: true).",
      -  "type": "boolean"
      -}
    • addedInput schema / properties / projectId
      Added value: +{
      +  "description": "Project UUID. Defaults to configured project. (`project_id` is accepted too.)",
      +  "type": "string"
      +}
    • removedInput schema / properties / project_id
      Removed value: -{
      -  "description": "Project UUID. Defaults to configured project.",
      -  "type": "string"
      -}
    • addedInput schema / properties / reportId
      Added value: +{
      +  "description": "Report UUID to triage. (`report_id` is accepted too.)",
      +  "format": "uuid",
      +  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      +  "type": "string"
      +}
    • removedInput schema / properties / report_id
      Removed value: -{
      -  "description": "Report UUID to triage.",
      -  "format": "uuid",
      -  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "report_id"
      -]New value: +[
      +  "reportId"
      +]
    • changedOutput schema / properties / blast_radius / anyOf
      Previous value: -[
      -  {},
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "affected": {
      +        "items": {},
      +        "type": "array"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / properties / blast_radius / description
      Added value: +"Downstream nodes of the inventory action the report is filed against, or null"
    • addedOutput schema / properties / category / description
      Added value: +"bug | slow | visual | confusing | other, or unknown"
    • addedOutput schema / properties / category / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / fix_context / anyOf
      Previous value: -[
      -  {},
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "bugOntologyTags": {
      +        "description": "Bug ontology tags, or null"
      +      },
      +      "component": {
      +        "description": "Component or page the bug was attributed to",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "fixPrompt": {
      +        "description": "Paste-ready fix prompt composed server-side, or null"
      +      },
      +      "reproductionSteps": {
      +        "description": "Reproduction steps recorded on the report ([] if none)"
      +      },
      +      "rootCause": {
      +        "description": "Stage-2 root cause, or null before Stage 2 runs"
      +      }
      +    },
      +    "required": [
      +      "fixPrompt",
      +      "reproductionSteps",
      +      "component",
      +      "rootCause",
      +      "bugOntologyTags"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / properties / fix_context / description
      Added value: +"Fix-context slice, as get_fix_context returns it"
    • addedOutput schema / properties / notes
      Added value: +{
      +  "description": "Sources that do not apply to this report, and why",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / partial_errors
      Added value: +{
      +  "description": "Sources that failed, as \"source: message\"",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / recent_logs / anyOf
      Previous value: -[
      -  {},
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "entries": {
      +        "items": {},
      +        "type": "array"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / properties / recent_logs / description
      Added value: +"Recent warn+ pipeline log entries for the project, or null"
    • addedOutput schema / properties / recommended_actions / description
      Added value: +"What to do next, most important first"
    • addedOutput schema / properties / recommended_actions / items / additionalProperties
      Added value: +false
    • addedOutput schema / properties / recommended_actions / items / properties
      Added value: +{
      +  "action": {
      +    "type": "string"
      +  },
      +  "args": {
      +    "additionalProperties": {},
      +    "description": "Arguments for that tool",
      +    "propertyNames": {
      +      "type": "string"
      +    },
      +    "type": "object"
      +  },
      +  "reason": {
      +    "type": "string"
      +  },
      +  "tool": {
      +    "description": "Tool to call next",
      +    "type": "string"
      +  }
      +}
    • addedOutput schema / properties / recommended_actions / items / required
      Added value: +[
      +  "action",
      +  "reason"
      +]
    • addedOutput schema / properties / recommended_actions / items / type
      Added value: +"object"
    • addedOutput schema / properties / report / anyOf
      Added value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "breadcrumbs": {},
      +      "category": {
      +        "description": "bug | slow | visual | confusing | other",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "child_report_ids": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "component": {
      +        "description": "Component or page the bug was attributed to",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "console_logs": {
      +        "description": "Console entries captured with the report"
      +      },
      +      "created_at": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "description": {
      +        "description": "What the reporter wrote (untrusted text)",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "environment": {
      +        "description": "Browser/OS/viewport the SDK captured"
      +      },
      +      "fix_attempts": {
      +        "description": "Latest fix attempts, newest first",
      +        "items": {
      +          "additionalProperties": {},
      +          "properties": {
      +            "id": {
      +              "type": "string"
      +            },
      +            "status": {
      +              "type": [
      +                "string",
      +                "null"
      +              ]
      +            }
      +          },
      +          "required": [
      +            "id"
      +          ],
      +          "type": "object"
      +        },
      +        "type": "array"
      +      },
      +      "fix_packet": {
      +        "description": "Paste-ready fix prompt composed server-side"
      +      },
      +      "id": {
      +        "description": "Report UUID",
      +        "type": "string"
      +      },
      +      "inventory_action": {
      +        "description": "Inventory action the report is filed against, when resolved"
      +      },
      +      "network_logs": {
      +        "description": "Network requests captured with the report"
      +      },
      +      "project_id": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "reproduction_steps": {},
      +      "screenshot_url": {
      +        "description": "Signed screenshot URL",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "severity": {
      +        "description": "critical | high | medium | low",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "stage1_classification": {
      +        "description": "Stage-1 (fast) classification"
      +      },
      +      "stage2_analysis": {
      +        "description": "Stage-2 analysis: rootCause, suggestedFix, …"
      +      },
      +      "status": {
      +        "description": "Workflow status, e.g. new, classified, fixing, fixed, verified, reopened",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "summary": {
      +        "description": "One-line summary written by the classifier",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "title": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      }
      +    },
      +    "required": [
      +      "id"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "error": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "error"
      +    ],
      +    "type": "object"
      +  }
      +]
    • addedOutput schema / properties / report / description
      Added value: +"The report (documented fields, no reporter identifiers), or the error reading it"
    • addedOutput schema / properties / report_id / description
      Added value: +"The triaged report UUID"
    • changedOutput schema / properties / reporter_thread / anyOf
      Previous value: -[
      -  {},
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "report_id": {
      +        "type": "string"
      +      },
      +      "timeline": {
      +        "items": {},
      +        "type": "array"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / properties / reporter_thread / description
      Added value: +"The unified report timeline (comments, fixes, QA), or null"
    • addedOutput schema / properties / severity / description
      Added value: +"critical | high | medium | low, or unknown when the report could not be read"
    • addedOutput schema / properties / severity / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / similar_bugs / anyOf
      Previous value: -[
      -  {},
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "category": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "createdAt": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "description": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "reportGroupId": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "reportId": {
      +          "type": "string"
      +        },
      +        "similarity": {
      +          "type": "number"
      +        }
      +      },
      +      "required": [
      +        "reportId",
      +        "similarity"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / properties / similar_bugs / description
      Added value: +"Up to five nearest reports by summary, excluding this one; null when not searched"
    • addedOutput schema / properties / status / description
      Added value: +"Workflow status, or unknown"
    • addedOutput schema / properties / status / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • addedOutput schema / properties / triage_summary / description
      Added value: +"One-line summary"
    • changedOutput schema / required
      Previous value: -[
      -  "report_id",
      -  "severity",
      -  "category",
      -  "status",
      -  "report",
      -  "reporter_thread",
      -  "similar_bugs",
      -  "fix_context",
      -  "blast_radius",
      -  "recent_logs",
      -  "recommended_actions",
      -  "triage_summary"
      -]New value: +[
      +  "report_id",
      +  "severity",
      +  "category",
      +  "status",
      +  "partial_errors",
      +  "notes",
      +  "report",
      +  "reporter_thread",
      +  "similar_bugs",
      +  "fix_context",
      +  "blast_radius",
      +  "recent_logs",
      +  "recommended_actions",
      +  "triage_summary"
      +]
  2. Changed2 schema fields changedv0.1.10
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / report_id / format
      Added value: +"uuid"
    • addedInput schema / properties / report_id / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  4. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds substantial behavior beyond that: it discloses that the tool merges multiple sources, returns recommended_actions, reports partial_errors for failed sources, and includes notes for non-applicable sources. This gives an agent an accurate mental model of what actually happens when the tool runs.

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?

The description is longer than a simple one-liner but is information-dense and front-loaded with the core purpose. The Sentry 'Analyze with Seer' analogy is helpful but slightly optional; otherwise each clause earns its place given the tool's complexity.

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?

Given the rich input schema, annotations, and presence of an output schema, the description is complete: it covers what sources are merged, what the returned packet contains, how failures/non-applicable sources are surfaced, and the intended call order before dispatch_fix. Nothing an agent needs 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%, so the schema fully documents reportId, projectId, and includeLogs. The description only adds 'Pass reportId to kick off review', which restates what the schema already conveys, so it does not go beyond the baseline.

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?

Description states a specific verb and resource: a 'read-only combined tool' that 'merges' six named sources into one 'structured review packet'. This clearly distinguishes it from the individual get_* siblings it aggregates, and the ordering hint 'Call this before dispatch_fix' anchors its role.

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?

The description gives explicit sequencing guidance ('Call this before dispatch_fix') and strongly implies the use case: a combined review packet with recommended actions when analyzing a user-felt report. However, it does not explicitly say when to prefer this over calling the individual get_* tools, or explicitly list when-not conditions.

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