User Intuition

Edit Research Output

edit_research_output

Destructive

Apply the requested prompt to an existing report or PowerPoint in place. Read the output first. Retains its ID and reuses saved evidence; default reports and Highlights cannot be edited. Poll inspect_research_session view=job and read the original output after success. Reuse the key on retry.

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>",
      "output_id": "<output_id>",
      "prompt": "<prompt>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "edit_research_output"
  }
}

Input Schema

Name	Required	Description
`prompt`	Yes	Natural-language question or instructions for the requested research task.
`output_id`	Yes	Identifier of the saved output, as returned by the output list or generation job.
`session_id`	Yes	UUID of the research session, as returned by inspect_research_session.
`idempotency_key`	Yes	Use a stable key for this operation and reuse it on retries with the same inputs.
`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.

Changed4 schema fields changedNov 9, 2026

addedInput schema / properties / idempotency_key / description

Added value: +"Use a stable key for this operation and reuse it on retries with the same inputs."

addedInput schema / properties / output_id / description

Added value: +"Identifier of the saved output, as returned by the output list or generation job."

addedInput schema / properties / prompt / description

Added value: +"Natural-language question or instructions for the requested research task."

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

A4.4/5.0

Behavior5/5

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

Annotations only declare destructiveHint=true / readOnlyHint=false / idempotentHint=false; the description adds substantive behavior beyond that: the edit happens in place, the output retains its ID and reuses saved evidence, certain output types are ineligible, the call is asynchronous and requires polling via inspect_research_session view=job, and the original output must be re-read afterward. It also explains retry semantics via the idempotency key, which the annotations do not cover.

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?

Six short sentences, front-loaded with the core action and followed by constraints, side effects, and polling. It is dense but every sentence carries information; the telegraphic "Poll inspect_research_session view=job" phrasing is efficient rather than padded, though it reads slightly clipped.

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 destructive, asynchronous, five-parameter mutation tool, the description covers preconditions, eligibility exclusions, in-place semantics, ID retention, polling, and retry behavior. Because an output schema exists, return-value detail is not required, and nothing an agent needs to invoke this correctly appears to be missing.

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

Parameters3/5

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

Schema description coverage is 100%, so every parameter is already documented in the schema, and the description adds little parameter-level detail beyond the retry instruction ("Reuse the key on retry"). The mention of the prompt and the output being read first is consistent with the schema but not additive. Baseline 3 is appropriate.

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?

"Apply the requested prompt to an existing report or PowerPoint in place" gives a specific verb (edit/apply), a specific resource (existing report or PowerPoint), and a distinguishing scope marker (in place, existing) that separates it from generating a new output. An agent can tell this is a mutation of a prior artifact rather than a fresh generation.

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 concrete preconditions ("Read the output first") and hard exclusions ("default reports and Highlights cannot be edited"), which is real when-not guidance. It does not explicitly name a sibling alternative such as generate_research_output for the non-editable cases, so it falls just short of full routing guidance.

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.