Annalist Financial Statements

Find the connections of 2 entities

find_connections

Read-onlyIdempotent

The shortest chain of links between 2 entities of Atlas, in either direction, and the counterparties that they share (the banks that lend to both, the customers of both, a common owner), each link with its summary, evidence and document ids. By default an entity of a covered group stands as its group, so that 2 banks of one group count as one lender.

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": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "find_connections"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	entity id from search_entities, for example caterpillar
`from`	Yes	entity id from search_entities, for example boeing
`group`	No	draw an entity of a covered group as its group (default true)
`kinds`	No	kinds of link to follow (default every kind)
`max_links`	No	longest chain to look for (default 4)

Output Schema

Name	Required	Description	Default
`to`	Yes
`from`	Yes
`note`	No
`page`	No
`path`	Yes
`group`	No
`kinds`	No
`shared`	Yes
`citation`	No
`shared_total`	Yes
`links_in_path`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds genuinely non-obvious behavior: links are traversed in either direction, only the shortest chain is returned, shared counterparties are surfaced alongside the chain, and by default an entity of a covered group is collapsed to its group. It does not state cost or latency behavior for deep searches.

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?

Two sentences, front-loaded with the core result and followed by a default-behavior caveat that an agent genuinely needs. The clause about 'summary, evidence and document ids' is largely redundant given a declared output schema, which is the only real waste.

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?

For a five-parameter, closed-world graph query with a full schema, 100% parameter coverage, annotations and an output schema, the description supplies everything an agent needs to call it correctly: scope, directionality, result composition, and the group-collapsing default. Return-value details are rightly left to the output schema.

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 100%, so the baseline is 3. The description still earns credit by giving meaning to the kinds filter through concrete examples (lender, customer, owner) and by explaining the group flag's practical effect ('2 banks of one group count as one lender'). It does not clarify how 'shortest chain' relates to the max_links bound beyond the schema's 'longest chain to look for'.

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 concrete operation on a concrete resource: the shortest chain of links between two named entities, plus shared counterparties, with parenthetical examples (banks lending to both, common owner). An agent can picture the result precisely. It does not explicitly contrast with the closest sibling, get_relationships, which also returns links but for a single entity, so it stops short of full sibling differentiation.

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

Usage Guidelines3/5

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

Usage is implied by the two-entity scope ('between 2 entities'), but there is no explicit when-to-use statement, no exclusion such as 'not for a single entity's links (use get_relationships)' and no mention of prerequisites like resolving ids via search_entities, which appears only in the schema. Adequate but leaves routing to inference.

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

All Annalist Financial Statements tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?