Skip to main content
Glama

fix_list

Turn a report into the things to do about it, one list per kind of work (bump a dependency, change the code, change the infrastructure, rotate a credential, wait for a release, decide), each most urgent first, each action saying how many…

Instructions

Turn a report into the things to do about it, one list per kind of work (bump a dependency, change the code, change the infrastructure, rotate a credential, wait for a release, decide), each most urgent first, each action saying how many findings it clears and what it ranks by. Every action is returned unless limit is set. Name the head of each list that applies: the lists are in a fixed order of kind, only priority compares an action in one list with an action in another, and which list to work from is the reader's choice. Name every action tied with the head of a list, not only the first. Actions tie when they have the same priority, exploitation, severity and number of findings cleared, and their order among themselves carries no meaning. Ask this rather than summarize_report when the question is what to change: one upgrade usually clears many findings, and an image somebody else publishes is one action however many packages are wrong inside it.

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": {
      "path": "<path>"
    },
    "name": "fix_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoonly the list for one kind of work: image (update an image the descriptor says somebody else builds), bump (upgrade a dependency), code (change the application's code or its server's configuration), infrastructure (change infrastructure code or a live setting), credential (remove and rotate a committed secret), wait (for somebody else's release) or decide (accept or replace, e.g. a license). Omit for every list
pathYespath to a results.sarif produced by draugr scan
limitNomaximum actions per list, except the image list, which is never cut; every action when omitted

Output Schema

NameRequiredDescriptionDefault
noteNo
listsYesone list per kind of work, ordered image, bump, code, infrastructure, credential, wait, decide; a kind with no action has no list
clearsYesfindings the returned actions clear between them, each counted once
totalClearsYesfindings the actions in every list clear between them, each counted once
totalActionsYesactions in every list, including any a limit left out

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.180.0
    • addedOutput schema / properties / lists / items / properties / actions / items / properties / beyond / description
      Added value: +"the size of a step past policy, minor or major"
    • addedOutput schema / properties / lists / items / properties / actions / items / properties / exploitation / properties / cve
      Added value: +{
      +  "description": "the CVE the dataset matched, present where ruleId names none",
      +  "type": "string"
      +}
    • changedOutput schema / properties / lists / items / properties / actions / items / properties / exploitation / properties / ruleId / description
      Previous value: -"the rule of the finding the signal applies to, a CVE"New value: +"the rule of the finding the signal applies to: a CVE, or an advisory id relating the CVE in cve"
    • addedOutput schema / properties / lists / items / properties / actions / items / properties / policy / description
      Added value: +"the largest upgrade step the component allows, patch or minor; absent where it allows any step"
    • addedOutput schema / properties / lists / items / properties / actions / items / properties / policyFrom
      Added value: +{
      +  "description": "the descriptor setting that set policy, e.g. config.fixes.upgrade; for a step past the policy, name it, since it is where the reader allows a larger step",
      +  "type": "string"
      +}
    • addedOutput schema / properties / lists / items / properties / actions / items / properties / withinPolicy / description
      Added value: +"false for a step larger than policy allows, which the reader has to choose to take"
  2. Changed4 schema fields changedv0.177.0
    • changedInput schema / properties / kind / description
      Previous value: -"only the list for one kind of work: bump (upgrade a dependency), code (change the application's code or its server's configuration), infrastructure (change infrastructure code or a live setting), credential (remove and rotate a committed secret), wait (for somebody else's release) or decide (accept or replace, e.g. a license). Omit for every list"New value: +"only the list for one kind of work: image (update an image the descriptor says somebody else builds), bump (upgrade a dependency), code (change the application's code or its server's configuration), infrastructure (change infrastructure code or a live setting), credential (remove and rotate a committed secret), wait (for somebody else's release) or decide (accept or replace, e.g. a license). Omit for every list"
    • changedInput schema / properties / limit / description
      Previous value: -"maximum actions per list; every action when omitted"New value: +"maximum actions per list, except the image list, which is never cut; every action when omitted"
    • changedOutput schema / properties / lists / description
      Previous value: -"one list per kind of work, ordered bump, code, infrastructure, credential, wait, decide; a kind with no action has no list"New value: +"one list per kind of work, ordered image, bump, code, infrastructure, credential, wait, decide; a kind with no action has no list"
    • changedOutput schema / properties / lists / items / properties / kind / description
      Previous value: -"bump, code, infrastructure, credential, wait or decide"New value: +"image, bump, code, infrastructure, credential, wait or decide"
  3. Changed1 schema field changedv0.174.0
    • addedOutput schema / properties / lists / items / properties / actions / items / properties / row
      Added value: +{
      +  "type": "string"
      +}
  4. Changed2 schema fields changedv0.166.3
    • changedOutput schema / properties / lists / items / properties / actions / items / properties / severity / description
      Previous value: -"the worst severity among the findings it clears, as ranked after KEV or EPSS raised one or reachability analysis lowered one: critical, high, medium or low"New value: +"the worst ranked severity among the findings it clears, after the control's minimum severity, KEV, EPSS and reachability analysis: critical, high, medium or low"
    • changedOutput schema / properties / lists / items / properties / actions / items / properties / severityFrom / description
      Previous value: -"the worst severity the scanners reported, present where KEV, EPSS or reachability analysis changed it"New value: +"the worst severity the scanners reported, present where the control's minimum severity, KEV, EPSS or reachability analysis changed it"
  5. Changed2 schema fields changedv0.166.0
    • changedOutput schema / properties / lists / items / properties / actions / items / properties / exploitation / description
      Previous value: -"the strongest exploitation evidence among the findings it clears, from the escalation of one of them; absent where KEV and EPSS raised none"New value: +"the strongest exploitation evidence among the findings it clears: a finding on KEV, whether or not KEV raised it, else one EPSS raised; absent where none is on KEV and EPSS raised none"
    • changedOutput schema / properties / lists / items / properties / actions / items / properties / exploitation / properties / ruleId / description
      Previous value: -"the rule of the finding the signal raised, a CVE"New value: +"the rule of the finding the signal applies to, a CVE"
  6. Changed7 schema fields changedv0.157.0
    • addedInput schema / properties / kind
      Added value: +{
      +  "description": "only the list for one kind of work: bump (upgrade a dependency), code (change the application's code or its server's configuration), infrastructure (change infrastructure code or a live setting), credential (remove and rotate a committed secret), wait (for somebody else's release) or decide (accept or replace, e.g. a license). Omit for every list",
      +  "type": "string"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"maximum actions to return; defaults to 20"New value: +"maximum actions per list; every action when omitted"
    • removedOutput schema / properties / actions
      Removed value: -{
      -  "description": "things to do, most urgent first; each says how many findings it clears",
      -  "items": {
      -    "additionalProperties": false,
      -    "properties": {
      -      "after": {
      -        "type": "string"
      -      },
      -      "beyond": {
      -        "type": "string"
      -      },
      -      "clears": {
      -        "type": "integer"
      -      },
      -      "component": {
      -        "type": "string"
      -      },
      -      "control": {
      -        "type": "string"
      -      },
      -      "ecosystem": {
      -        "type": "string"
      -      },
      -      "findings": {
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": [
      -          "null",
      -          "array"
      -        ]
      -      },
      -      "fixedVersions": {
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": [
      -          "null",
      -          "array"
      -        ]
      -      },
      -      "from": {
      -        "type": "string"
      -      },
      -      "id": {
      -        "type": "string"
      -      },
      -      "kind": {
      -        "type": "string"
      -      },
      -      "locations": {
      -        "items": {
      -          "additionalProperties": false,
      -          "properties": {
      -            "kind": {
      -              "type": "string"
      -            },
      -            "line": {
      -              "type": "integer"
      -            },
      -            "path": {
      -              "type": "string"
      -            },
      -            "repository": {
      -              "type": "string"
      -            }
      -          },
      -          "required": [
      -            "path",
      -            "kind"
      -          ],
      -          "type": "object"
      -        },
      -        "type": [
      -          "null",
      -          "array"
      -        ]
      -      },
      -      "package": {
      -        "type": "string"
      -      },
      -      "policy": {
      -        "type": "string"
      -      },
      -      "policyApplies": {
      -        "type": [
      -          "null",
      -          "boolean"
      -        ]
      -      },
      -      "priority": {
      -        "type": "string"
      -      },
      -      "ruleIds": {
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": [
      -          "null",
      -          "array"
      -        ]
      -      },
      -      "summary": {
      -        "type": "string"
      -      },
      -      "target": {
      -        "type": "string"
      -      },
      -      "title": {
      -        "type": "string"
      -      },
      -      "upstream": {
      -        "type": "boolean"
      -      },
      -      "versioning": {
      -        "type": "string"
      -      },
      -      "where": {
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": [
      -          "null",
      -          "array"
      -        ]
      -      },
      -      "withinPolicy": {
      -        "type": [
      -          "null",
      -          "boolean"
      -        ]
      -      }
      -    },
      -    "required": [
      -      "id",
      -      "title",
      -      "kind",
      -      "clears"
      -    ],
      -    "type": "object"
      -  },
      -  "type": [
      -    "null",
      -    "array"
      -  ]
      -}
    • addedOutput schema / properties / lists
      Added value: +{
      +  "description": "one list per kind of work, ordered bump, code, infrastructure, credential, wait, decide; a kind with no action has no list",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "actions": {
      +        "description": "things to do, most urgent first: by priority, then exploitation, then severity, then how many findings each clears",
      +        "items": {
      +          "additionalProperties": false,
      +          "properties": {
      +            "after": {
      +              "type": "string"
      +            },
      +            "beyond": {
      +              "type": "string"
      +            },
      +            "clears": {
      +              "type": "integer"
      +            },
      +            "component": {
      +              "type": "string"
      +            },
      +            "control": {
      +              "type": "string"
      +            },
      +            "ecosystem": {
      +              "type": "string"
      +            },
      +            "exploitation": {
      +              "additionalProperties": false,
      +              "description": "the strongest exploitation evidence among the findings it clears, from the escalation of one of them; absent where KEV and EPSS raised none",
      +              "properties": {
      +                "asOf": {
      +                  "description": "the day the dataset was obtained, YYYY-MM-DD",
      +                  "type": "string"
      +                },
      +                "detail": {
      +                  "description": "the specific fact, e.g. on KEV or EPSS 0.87",
      +                  "type": "string"
      +                },
      +                "ruleId": {
      +                  "description": "the rule of the finding the signal raised, a CVE",
      +                  "type": "string"
      +                },
      +                "signal": {
      +                  "description": "kev (observed exploitation) or epss (predicted probability of exploitation)",
      +                  "type": "string"
      +                }
      +              },
      +              "required": [
      +                "signal",
      +                "ruleId"
      +              ],
      +              "type": [
      +                "null",
      +                "object"
      +              ]
      +            },
      +            "findings": {
      +              "items": {
      +                "type": "string"
      +              },
      +              "type": [
      +                "null",
      +                "array"
      +              ]
      +            },
      +            "fixedVersions": {
      +              "items": {
      +                "type": "string"
      +              },
      +              "type": [
      +                "null",
      +                "array"
      +              ]
      +            },
      +            "from": {
      +              "type": "string"
      +            },
      +            "id": {
      +              "type": "string"
      +            },
      +            "kind": {
      +              "type": "string"
      +            },
      +            "locations": {
      +              "items": {
      +                "additionalProperties": false,
      +                "properties": {
      +                  "kind": {
      +                    "type": "string"
      +                  },
      +                  "line": {
      +                    "type": "integer"
      +                  },
      +                  "path": {
      +                    "type": "string"
      +                  },
      +                  "repository": {
      +                    "type": "string"
      +                  }
      +                },
      +                "required": [
      +                  "path",
      +                  "kind"
      +                ],
      +                "type": "object"
      +              },
      +              "type": [
      +                "null",
      +                "array"
      +              ]
      +            },
      +            "package": {
      +              "type": "string"
      +            },
      +            "policy": {
      +              "type": "string"
      +            },
      +            "policyApplies": {
      +              "type": [
      +                "null",
      +                "boolean"
      +              ]
      +            },
      +            "priority": {
      +              "type": "string"
      +            },
      +            "ruleIds": {
      +              "items": {
      +                "type": "string"
      +              },
      +              "type": [
      +                "null",
      +                "array"
      +              ]
      +            },
      +            "severity": {
      +              "description": "the worst severity among the findings it clears, as ranked after KEV or EPSS raised one or reachability analysis lowered one: critical, high, medium or low",
      +              "type": "string"
      +            },
      +            "severityFrom": {
      +              "description": "the worst severity the scanners reported, present where KEV, EPSS or reachability analysis changed it",
      +              "type": "string"
      +            },
      +            "summary": {
      +              "type": "string"
      +            },
      +            "target": {
      +              "type": "string"
      +            },
      +            "title": {
      +              "type": "string"
      +            },
      +            "upstream": {
      +              "type": "boolean"
      +            },
      +            "versioning": {
      +              "type": "string"
      +            },
      +            "where": {
      +              "items": {
      +                "type": "string"
      +              },
      +              "type": [
      +                "null",
      +                "array"
      +              ]
      +            },
      +            "withinPolicy": {
      +              "type": [
      +                "null",
      +                "boolean"
      +              ]
      +            }
      +          },
      +          "required": [
      +            "id",
      +            "title",
      +            "kind",
      +            "clears"
      +          ],
      +          "type": "object"
      +        },
      +        "type": [
      +          "null",
      +          "array"
      +        ]
      +      },
      +      "kind": {
      +        "description": "bump, code, infrastructure, credential, wait or decide",
      +        "type": "string"
      +      },
      +      "name": {
      +        "description": "the list's name as the console prints it",
      +        "type": "string"
      +      },
      +      "totalActions": {
      +        "description": "actions in this list, including any a limit left out",
      +        "type": "integer"
      +      },
      +      "totalClears": {
      +        "description": "findings this list's actions clear between them, each counted once",
      +        "type": "integer"
      +      }
      +    },
      +    "required": [
      +      "kind",
      +      "name",
      +      "actions",
      +      "totalActions",
      +      "totalClears"
      +    ],
      +    "type": "object"
      +  },
      +  "type": [
      +    "null",
      +    "array"
      +  ]
      +}
    • changedOutput schema / properties / totalActions / description
      Previous value: -"actions the report implies, returned or not"New value: +"actions in every list, including any a limit left out"
    • changedOutput schema / properties / totalClears / description
      Previous value: -"findings every action clears between them, each counted once"New value: +"findings the actions in every list clear between them, each counted once"
    • changedOutput schema / required
      Previous value: -[
      -  "actions",
      -  "clears",
      -  "totalActions",
      -  "totalClears"
      -]New value: +[
      +  "lists",
      +  "clears",
      +  "totalActions",
      +  "totalClears"
      +]
  7. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses that all actions are returned unless limit is set, that lists are in a fixed order of kind, that only priority is comparable across lists, and that tie order among equally-ranked actions is meaningless. It does not cover failure modes (bad path, non-SARIF input) or what the output schema delivers, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening clause is front-loaded and the content is substantive, but the prose is dense and convoluted — long run-on sentences with heavy parentheticals ('bump a dependency, change the code, change the infrastructure, rotate a credential, wait for a release, decide') that restate the kind enum. The tie-breaking and list-ordering rules are buried mid-paragraph rather than given their own structure.

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?

An output schema exists, so return values need not be explained, and the description still covers the semantics an agent needs: grouping, ordering, tie behavior, and the limit exception. Missing pieces are minor — input preconditions for path and how to interpret the returned structure below the list-head level.

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 kind, path and limit are already fully documented with the image-list exception baked into the schema. The description adds meaning at the list level ('one list per kind of work', cross-list comparison only by priority) but adds no syntax, default or format detail beyond the schema. 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?

The description conveys a specific transformation — turning a scan report into grouped, prioritized action lists ('one list per kind of work... each most urgent first') — and it names what each action carries (findings cleared, ranking basis). It never states the plain resource-and-verb form (e.g. 'list fix actions from a results.sarif'), relying on metaphor ('turn a report into the things to do about it'), which slightly blunts first-read clarity, but an agent can still distinguish it from summarize_report.

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

Usage Guidelines5/5

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

Explicit routing is given: 'Ask this rather than summarize_report when the question is what to change', followed by the reason (one upgrade clears many findings; a single image is one action however many packages are wrong inside it). It also tells the agent how to present results — name the head of each applicable list, and name every action tied with the head — which is concrete invocation guidance rather than inference.

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