BeliefState

Get research visual

get_visual

Retrieves saved research charts and tables for one investment case or context assessment. Without visual_id, returns available visual and region descriptors; with visual_id, returns the selected visual's regions. Supply region_id for available structured chart/table data, with bounded row pagination. Results preserve citations, recorded coverage, historical cutoffs and text-access restrictions. Use visual_offset for another descriptor page, without visual_id. Uses account allowance or prepaid credit.

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": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "get_visual"
  }
}

Input Schema

Name	Required	Description
`as_of`	No
`context`	Yes	User's research goal in one short sentence (max 300 characters); include relevant ticker and topic. Exclude names, contact/account/portfolio details, credentials and source text.
`belief_id`	No
`llm_model`	Yes	Your model identifier, if known (e.g. gpt-6); otherwise leave unknown. Exclude credentials and private deployment names.
`region_id`	No	Use a region_id returned in the selected visual's regions to retrieve structured data.
`row_limit`	No	Rows or chart points per read; defaults to 50, maximum 100.
`visual_id`	No	Omit to list saved visuals; supply a returned visual_id to inspect it.
`row_offset`	No	Zero-based starting row or chart-point index in the selected region.
`region_offset`	No	Continue a selected visual's region descriptors using next_region_offset.
`visual_offset`	No	Continue visual descriptors using next_visual_offset; requires belief_id and cannot accompany visual_id.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.
`context_assessment_id`	No	Open a neutral engine context assessment returned by a brief or ordered change. It is not an author Belief.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Goes beyond annotations by disclosing cost ('Uses account allowance or prepaid credit'), result guarantees (citations preserved, recorded coverage, historical cutoffs, text-access restrictions), and bounded row pagination. These explain why readOnlyHint=false despite retrieval semantics, so no contradiction, though the access-control/entitlement behavior of 'text-access restrictions' is left unexpanded.

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?

Front-loaded with purpose, then ordered by retrieval stage, with no filler sentences. Dense compressed phrasing ('recorded coverage', 'historical cutoffs') is efficient but slightly opaque on first read.

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 12-parameter, multi-mode tool with an output schema, the description covers the mode switch, pagination continuation, cost model, and result properties an agent needs before calling. Remaining details (as_of, belief_id linkage, conversation_id reuse) are fully specified in the high-coverage 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?

With 83% schema coverage the baseline is 3, but the description adds the retrieval hierarchy that individual parameter docs do not: descriptors → visual → regions → rows, including that visual_offset applies only to the descriptor level and is mutually exclusive with visual_id. It does not clarify as_of, belief_id, or conversation reuse beyond what the schema already says.

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?

States a specific verb and resource ('Retrieves saved research charts and tables') plus its scope ('for one investment case or context assessment'), and immediately enumerates the two operating modes. No sibling tool in the list handles visuals, so an agent can distinguish it without opening the 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?

The description gives explicit mode-selection rules: omit visual_id to list descriptors, supply it to get regions, add region_id for structured data, use visual_offset for another descriptor page. It lacks explicit when-not-to-use guidance or named alternatives among siblings (e.g., versus get_case or get_brief for case context).

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

All BeliefState 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.