Mipiti MCP Server

Overview Schema Source Related Servers Discussions Admin

Get Verdict Divergence

get_verdict_divergence

Surface where LLM verdicts disagree with a threat model's authored mappings, showing missing or spurious coverage to accept or dismiss.

Instructions

Where the LLM's verdicts disagree with the model's authored state.

Two coverage divergence kinds, distinguished by the LLM's p_covers (probability the control covers the CO), shown as "model confidence":

missing_mapping: HIGH p_covers, but the CO is NOT mapped — the LLM is confident the control covers it, so it should be mapped. Accepting ADDS the mapping.
spurious_mapping: LOW p_covers, but the CO IS mapped — the LLM is confident the control does NOT cover it, so the mapping is likely wrong and inflates apparent coverage. Accepting REMOVES the mapping. Only confident rows surface; the uncertain middle band is dropped. So a ~100%-confidence row is a strong "add" and a ~0%-confidence row is a strong "remove" — both are actionable, in opposite directions.

Rows are sorted by confidence, so the strongest calls come first. Each section is paginated: its pagination.filtered_total reports the full count, so when it exceeds the rows returned, raise limit (up to 500) or page with offset to review every divergence — not only the first page.

Also returns group_sufficiency divergences (observation-only). Apply coverage rows with resolve_verdict_divergences(action="accept"); set aside rows the structural model got right with resolve_verdict_divergences(action="dismiss").

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Optional filter — "missing_mapping", "spurious_mapping", or "group_sufficiency". Empty returns all kinds.
`limit`	No	Max rows per section (clamped to 1-500, default 100). Set to 500 to pull an entire section in one call.
`offset`	No	Skip the first N rows of each section, for pagination.
`model_id`	Yes	ID of the threat model.
`server_version`	Yes
`include_dismissed`	No	When true, return ONLY previously-dismissed rows (the undo view) instead of the active list.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.66.0Aug 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: only confident rows surface, the uncertain middle band is dropped, rows are sorted by confidence, and accepting a row either ADDS or REMOVES a mapping depending on kind. It also discloses pagination semantics (pagination.filtered_total) and the limit clamp. This is rich behavioral disclosure beyond any structured field.

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 purpose is front-loaded and the bulleted breakdown of the two kinds is scannable. It runs long, and the sentence restating that ~100% confidence means 'add' and ~0% means 'remove' is partly redundant with the bullets above it, but overall the structure is efficient for the workflow described.

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?

An output schema exists, so return values need not be re-explained, yet the description still supplies the operational context an agent needs: the two-kind model, direction of effect, confidence sorting, pagination, and the resolve/dismiss resolution path. Nothing required to call this correctly or act on its output is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 83%, so the baseline is 3, but the description adds genuine value beyond the schema: it explains the meaning of the two kind values and group_sufficiency, and clarifies limit (raise up to 500 to pull a whole section) and offset in terms of per-section pagination. The include_dismissed undo-view semantics are left to the schema.

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?

The opening line precisely defines the resource: rows where the LLM's verdicts disagree with the model's authored state. It names the two divergence kinds (missing_mapping, spurious_mapping) and explicitly distinguishes this read-only retrieval tool from the sibling that acts on it, resolve_verdict_divergences. An agent can tell what this returns and how it differs from get_sufficiency or model_coherence_report without opening a schema.

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 routing guidance: apply coverage rows via resolve_verdict_divergences(action="accept"), set aside model-correct rows with action="dismiss", and treat group_sufficiency as observation-only. It also instructs when to raise limit or page with offset. It stops short of an explicit 'use this when X instead of Y' statement versus sibling diagnostic tools, but the next-step guidance is strong.

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

Deploy Server