Research Toolkit

Overview Schema Source Related Servers Discussions Admin

research_review

Run content reviews and audits on research tasks, retaining original evidence. Choose self-review, external, or independent reviewer modes.

Instructions

Run the configured content reviews and any declared audits, retaining original evidence. Without a configured backend, new tasks return a self-review prompt; submit the actual result as self_review. Explicit external/independent selections never silently downgrade. Lite returns explicit skip logs. External calls send the full task/report/evidence to the configured model account. May consume its usage. evidence_paths are UTF-8 files relative to the task; required registry materials are included automatically. Use evidence_path in source records for local source text/extracts. Use purpose=evaluation to preserve defects. Resume incomplete assignments; never retry a valid negative result to improve the verdict. After correcting a report, pass revision=True for its new version; this is the normal report-delivery loop. Already authorized corrections do not need another user confirmation. Reconcile changed scope in task records first. For local self-review, include_assignment=False returns the frozen input path/hash instead of repeating its full text. Read the current assignment locally and reuse already-read unchanged evidence; review and freshness checks are identical.

Input Schema

TableJSON Schema

Name	Required	Default
`task`	Yes
`purpose`	No	report_delivery
`artifact`	No	final.md
`reviewer`	No
`revision`	No
`self_review`	No
`evidence_paths`	Yes
`include_assignment`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Oct 15, 2026

TDQS

A4/5.0

Behavior5/5

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

With no annotations, the description carries the full behavioral burden and discloses important side effects: external calls send the full task/report/evidence to the configured model account and may consume usage. It also documents non-obvious policies such as no silent downgrade, explicit skip logs, retained evidence, and retry limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and contains little outright fluff, but it is a dense block of operational rules without grouping or headings. The final sentence about reading the assignment locally is awkwardly placed and the overall structure makes the guidance harder to scan than it needs to 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?

Given the complex review workflow, missing annotations, and 0% schema description coverage, the description supplies substantial operational context. It is not fully complete because some parameters remain vague and output behavior is not explained, though the presence of an output schema reduces the need for return-value detail.

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 0%, so the description must compensate. It usefully explains evidence_paths format, purpose=evaluation, revision=True, include_assignment=False, and self_review usage, but leaves other parameters such as artifact and task format largely undocumented.

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 states a specific verb and resource: run configured content reviews and declared audits while retaining original evidence. It is clear enough to distinguish from generic workflow tools, but it does not explicitly distinguish itself from sibling tools such as research_check_draft or research_check_reviewer.

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 many conditional usage rules: submit self_review when no backend is configured, use purpose=evaluation to preserve defects, resume incomplete assignments, avoid retrying valid negatives, and pass revision=True after corrections. It covers when to do many things, though it does not name sibling alternatives.

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

Deploy Server