Skip to main content
Glama

update_vulnerability

Idempotent

Update vulnerable item or remediation task records, including assignment and notes, and request deferrals through an exception approval without changing the shared CVE library.

Instructions

Update a vulnerable item (VIT) or remediation task (VUL) (requires WRITE_ENABLED=true). Never writes the shared CVE library (sn_vul_entry). A deferral (state deferred, or defer_until) is requested through an exception request (sn_vul_change_approval) so it goes through approval

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": {
      "sys_id": "<sys_id>"
    },
    "name": "update_vulnerability"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldsNoFields to update (state as a label or number, assignment_group, work_notes, etc.)
reasonNoDeferral reason (required with defer_until)
sys_idYessys_id, VIT... or VUL... of the record to update
defer_untilNoRequest a deferral until this date (YYYY-MM-DD) instead of setting the state
compensating_controlsNoCompensating controls for the deferral

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv5.1.0
    • addedInput schema / properties / compensating_controls
      Added value: +{
      +  "description": "Compensating controls for the deferral",
      +  "type": "string"
      +}
    • addedInput schema / properties / defer_until
      Added value: +{
      +  "description": "Request a deferral until this date (YYYY-MM-DD) instead of setting the state",
      +  "type": "string"
      +}
    • changedInput schema / properties / fields / description
      Previous value: -"Fields to update (state, risk_acceptance_notes, remediation_date, etc.)"New value: +"Fields to update (state as a label or number, assignment_group, work_notes, etc.)"
    • addedInput schema / properties / reason
      Added value: +{
      +  "description": "Deferral reason (required with defer_until)",
      +  "type": "string"
      +}
    • changedInput schema / properties / sys_id / description
      Previous value: -"System ID of the vulnerability entry"New value: +"sys_id, VIT... or VUL... of the record to update"
    • changedInput schema / required
      Previous value: -[
      -  "sys_id",
      -  "fields"
      -]New value: +[
      +  "sys_id"
      +]
  2. First observedv1.0.2

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true, so the safety profile is partly covered. The description adds real context the annotations cannot: an environment gating flag (WRITE_ENABLED=true), a hard scope boundary (never writes sn_vul_entry), and the fact that deferrals trigger an approval workflow rather than taking effect directly. It does not describe partial-update semantics or error behavior, which keeps it from 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.

Conciseness5/5

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

Three tight sentences, front-loaded with the operation and resource, then the gating precondition, then the scope boundary, then the deferral caveat. No sentence is redundant with the structured fields and there is no filler.

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?

For a write tool with a nested free-form 'fields' object and no output schema, the description covers the critical unknowns: the write enablement flag, what must never be touched, and how deferrals actually happen. It is silent on return value and on what a successful partial update looks like, a minor gap given no output schema exists.

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 all five parameters already carry their own documentation, making 3 the baseline. The description adds one genuinely new semantic link: defer_until / deferred state routes through the exception-request approval flow, which explains why those parameters exist together. It adds nothing about the nested 'fields' object's allowed values or format.

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 (update) and precise resource scope: vulnerable item (VIT) or remediation task (VUL), with the record prefixes spelled out. The domain-specific naming (VIT/VUL) lets an agent distinguish this from generic siblings like update_record or update_incident, though it never names an explicit alternative.

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 concrete preconditions and routing: WRITE_ENABLED=true is required, the shared CVE library (sn_vul_entry) is off-limits, and a deferral must instead be requested through an exception request (sn_vul_change_approval). That redirect is exactly the kind of when-to-use-this-vs-elsewhere guidance agents need, though no sibling tool is named as the alternative path.

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