Skip to main content
Glama
MarkAC007

mcp-server-scf

by MarkAC007
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

scf_review_evidence_assessment

Record human decisions on AI evidence assessments by confirming the verdict or overriding it with a reason and at least one objective re-designation.

Instructions

Record a human decision on a file's current AI assessment (write — editor role). confirmed keeps the verdict; overridden needs a reason and at least one objective re-designation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
org_idYesOrganization UUID — obtain from scf_list_organizations
reasonNoWhy the verdict is overridden — required when decision is overridden
file_idYesEvidence file UUID — obtain from scf_list_evidence_files
decisionYesconfirmed = AI verdict stands; overridden = you are changing it
evidence_idYesCatalog evidence ID the file belongs to, e.g. E-IAM-01
ao_overridesNoObjectives to re-designate — required (≥1) when overriding, forbidden when confirming; unlisted objectives keep the AI's designation. 422 if the version has no per-objective answers: confirm instead

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.5.0
    • changedInput schema / properties / ao_overrides / description
      Previous value: -"Objectives to re-designate — required (≥1) when overriding, forbidden when confirming; unlisted objectives keep the AI's designation"New value: +"Objectives to re-designate — required (≥1) when overriding, forbidden when confirming; unlisted objectives keep the AI's designation. 422 if the version has no per-objective answers: confirm instead"
    • addedInput schema / properties / ao_overrides / items / properties / ao_id / minLength
      Added value: +1
  2. Addedv3.4.2

TDQS

A4/5.0
Behavior4/5

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

Annotations only mark it as not read-only and not destructive; the description adds meaningful behavior: 'confirmed keeps the verdict' while 'overridden needs a reason and at least one objective re-designation,' and it states the editor role. It does not detail side effects like overwriting prior human decisions, but the core write behavior is transparent.

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?

Two compact sentences front-load the primary action and then give the key conditional rule. There is no redundant restatement of parameter names or schema fields.

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?

The schema already documents all parameters, required fields, and the 422 condition for missing per-objective answers. The description adds the role and decision semantics, leaving no critical gap for invoking the tool, though it does not describe the response payload.

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 the baseline is 3. The description's mention of 'reason and at least one objective re-designation' echoes the schema's own conditional requirements without adding new syntax or format details, so no uplift is warranted.

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 names a specific action ('Record a human decision on a file's current AI assessment') with an explicit write/editor role. The confirmed/overridden distinction clarifies what the tool does, but it does not explicitly name or contrast sibling tools like scf_review_evidence_file, so differentiation is implicit.

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?

It gives clear context: this is for a human editor recording a decision about an AI assessment, and it specifies which decision requires extra inputs. It does not explicitly state when not to use it or point to an alternative tool, but the context is sufficient to infer the intended use-case.

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