User Intuition

Upload Research Template

upload_research_template

Upload a template up to 5 MB: report Markdown/TXT/DOCX with {{title}} and/or {{findings}} placeholders; presentation 16:9 PPTX theme/layout. Send raw file bytes as base64; pass the returned template id to generate_research_output. Repeated uploads create separate templates.

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": {
      "session_id": "<session_id>",
      "kind": "<kind>",
      "file_name": "<file_name>",
      "data_base64": "<data_base64>"
    },
    "name": "upload_research_template"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes	Choose whether the file is a report template or a presentation template.
`file_name`	Yes	Base filename of the uploaded file, including its extension.
`session_id`	Yes	UUID of the research session, as returned by inspect_research_session.
`data_base64`	Yes	Raw file bytes encoded as standard base64; never a server path or URL.
`organization_id`	No	Organization for this operation and billing. Use list_organizations to choose an active membership.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 9, 2026

addedInput schema / properties / file_name / description

Added value: +"Base filename of the uploaded file, including its extension."

addedInput schema / properties / kind / description

Added value: +"Choose whether the file is a report template or a presentation template."

addedInput schema / properties / session_id / description

Added value: +"UUID of the research session, as returned by inspect_research_session."

Changed1 schema field changedOct 22, 2026

changedInput schema / properties / organization_id / description

Previous value: -"Platform admins only: select an organization for this operation. Required when changing another organization’s study or using its wallet."New value: +"Organization for this operation and billing. Use list_organizations to choose an active membership."

AddedOct 17, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, and the description reinforces this with the concrete consequence ('repeated uploads create separate templates'), which explains the non-idempotent hint. It adds a hard 5 MB ceiling and per-kind format/placeholder requirements that the annotations cannot express. It says nothing about authentication, organization/billing scoping, or failure modes for oversized/invalid files.

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 first sentence front-loads the size limit and the two format branches, followed by the base64 transport rule, the downstream handoff, and the duplication caveat — no filler. The density of semicolon-separated clauses makes it slightly harder to scan than a short bulleted breakdown would be.

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?

With an output schema present, the description rightly avoids describing return values and instead points to the returned template id. For a 5-parameter upload with a size cap and format constraints, it covers the decisions an agent must make (which kind, what file, how to encode, what to do next); only organization/session prerequisites are left implicit in the 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 adds real meaning by tying the `kind` enum values to concrete file requirements (report → Markdown/TXT/DOCX with placeholders, presentation → 16:9 PPTX) and by reiterating that `data_base64` must be raw bytes rather than a path or URL. It does not explain `organization_id` or the session scoping, leaving those 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?

States a specific verb and resource ('Upload a template') and immediately scopes it by artifact type: report Markdown/TXT/DOCX with {{title}}/{{findings}} placeholders versus a 16:9 PPTX presentation theme/layout. It also names the downstream sibling (generate_research_output), so an agent can distinguish this template-upload tool from the source-upload sibling without opening either 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?

Gives clear downstream context — 'pass the returned template id to generate_research_output' — and warns that 'repeated uploads create separate templates,' which tells the agent not to retry blindly. It does not explicitly contrast itself with upload_research_source (document/source ingestion vs. template ingestion), which is the most likely confusion given the sibling set.

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

All User Intuition 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.