Skip to main content
Glama
Mipiti
by Mipiti

list_reconciliation_candidates

Lists pending or rejected duplicate-entity matches between a threat model and its ancestors, separating certain from heuristic matches, so operators can triage and resolve duplicates before they distort coverage.

Instructions

Reconciliation triage surface between this model and its ancestors.

When a model inherits entities (assets, attackers, components, trust boundaries) from an ancestor and the operator has authored a locally-named entity that looks like the same real-world thing, the reconciliation engine pairs them so the operator can decide whether to alias the local entity onto the inherited qualified id. disposition selects which side of the triage queue to read:

  • disposition="active" (default) — the OPEN candidate queue: detected pairs the operator has not yet acted on. Tier certain is a deterministic match (same qid or structurally identical) and is safe to auto-apply via apply_certain_reconciliation_match; tier heuristic is a fuzzy name/description match that needs review. Previously-rejected pairs are filtered out of this queue. Paginated via page / page_size. Returns {model_id, flag_enabled, total, tiers: {certain: int, heuristic: int}, page, page_size, candidates: [{kind, own_qid, inherited_qid, tier: "certain"|"heuristic", reasons: [str, ...]}, ...]}. When composition is disabled on the backend, total is 0, candidates is empty, and flag_enabled: false.

  • disposition="rejected" — the operator's persisted "these are NOT duplicates" decisions, in rejected_at ascending order (the same set the candidate detector consults to filter the active queue). Use this to render the rejected section of a triage view, or to find the surrogate id needed by unreject_reconciliation_candidate. NOT paginated — page / page_size are ignored. Returns {model_id, flag_enabled, rejections: [{id, model_id, kind, own_qid, inherited_qid, rejected_by, rejected_at}, ...]}. When composition is disabled on the backend, rejections is empty and flag_enabled: false; the same empty list is returned with flag_enabled: true when the rejection store is not configured on the instance.

Use on child models in a recursive tree to find duplicates that should be collapsed before they distort coverage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoACTIVE disposition only. 1-indexed page number. Default 1. Ignored when ``disposition="rejected"``.
model_idYesID of the descendant threat model.
page_sizeNoACTIVE disposition only. Items per page. Default 50. Ignored when ``disposition="rejected"``.
dispositionNoWhich side of the queue to read — ``"active"`` (default, open candidates) or ``"rejected"`` (persisted not-a-duplicate decisions).active
server_versionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

No annotations are provided, but the description fully discloses behavior: pagination details, the fact that rejected pairs are filtered out of the active queue, that rejected is not paginated, and edge cases when composition is disabled or rejection store is not configured. It also describes the return structure and tier semantics.

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 long but well-structured with clear sections for each disposition. It is front-loaded with its purpose and uses bullet-like formatting. While every sentence adds value, it could be tightened without losing essential details.

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?

The description covers all aspects: use cases, two modes, parameter behavior, pagination, edge cases (composition disabled, rejection store not configured), and return structures. It is complete given the tool's complexity and the presence of an output schema.

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

Parameters5/5

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

The description adds substantial meaning to parameters: it explains the disposition values and their implications, that page/page_size are only for active disposition and are ignored for rejected, and describes the structure of candidates and rejections. Schema coverage is 80%, and the description compensates fully.

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 description clearly states its role as a 'reconciliation triage surface' and explains the pairing of local entities with inherited qualified IDs. It explicitly distinguishes between active and rejected dispositions and references sibling tools like apply_certain_reconciliation_match, providing specific context for its use.

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 advises using the tool 'on child models in a recursive tree to find duplicates that should be collapsed before they distort coverage.' It also explains when to use each disposition (active vs. rejected) and mentions that certain tier matches are 'safe to auto-apply via apply_certain_reconciliation_match,' but does not explicitly contrast with all alternative tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Mipiti/mipiti-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server