BlindReview MCP

Overview Schema Source Related Servers Discussions Admin

Blind independent review of a decision

review_decision

Read-only

Get one independent external review before an expensive decision. The reviewer solves the problem blind, then compares your proposal and returns a verdict.

Instructions

Get ONE independent external review before an expensive decision (architecture, DB schema/migration, public API, key dependency, large refactor, security/performance, multi-hypothesis debugging). Default blind_first: the reviewer first solves the problem WITHOUT seeing proposed_solution, then the proposal is revealed and compared. Returns a compact verdict (KEEP | MODIFY | REPLACE | INSUFFICIENT_EVIDENCE), risks, an optional better alternative and the cheapest falsification probe to run. Costs one or two LLM calls; skip it for trivial changes (see should_review). BLINDNESS CONTRACT: describe the problem in objective/constraints/context/environment/evidence and put your plan ONLY in proposed_solution. Do not mention, hint at or paraphrase your planned solution in the other fields. decision_type and risk_level are visible to the blind phase. If proposed_solution is largely copied into the other fields, blind_first refuses with BLINDNESS_LEAK.

Input Schema

Name	Required	Description
`context`	Yes	Relevant facts about the codebase/system (summaries and key snippets). Describe the problem only. Do NOT put your planned solution, preferred approach or its wording here; it belongs in proposed_solution only (the blind phase must not see it).
`evidence`	No	Observed facts: logs, error messages, benchmark numbers, test output. Describe the problem only. Do NOT put your planned solution, preferred approach or its wording here; it belongs in proposed_solution only (the blind phase must not see it).
`objective`	Yes	The goal / problem to solve, not the solution. Describe the problem only. Do NOT put your planned solution, preferred approach or its wording here; it belongs in proposed_solution only (the blind phase must not see it).
`risk_level`	Yes	Visible to the blind phase by design.
`constraints`	Yes	Hard requirements: compatibility, SLAs, deadlines, forbidden approaches. Describe the problem only. Do NOT put your planned solution, preferred approach or its wording here; it belongs in proposed_solution only (the blind phase must not see it).
`environment`	No	Runtime/deploy environment: versions, topology, scale, traffic. Describe the problem only. Do NOT put your planned solution, preferred approach or its wording here; it belongs in proposed_solution only (the blind phase must not see it).
`review_mode`	No	blind_first (default): reviewer forms an independent position before seeing the proposal. proposal_first: control mode, plain critique.
`decision_type`	Yes	Visible to the blind phase by design.
`proposed_solution`	Yes	Your proposed solution. The ONLY field that may describe it. Hidden from the reviewer until phase 2 in blind_first mode.

Output Schema

Name	Required	Description	Default
`meta`	Yes
`verdict`	Yes
`confidence`	Yes
`material_risks`	Yes
`recommendation`	Yes
`better_alternative`	No
`falsification_probe`	Yes
`critical_assumptions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.0Oct 7, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, but the description adds substantial non-obvious behavior: cost ('one or two LLM calls'), the two-phase blind protocol, the refusal path (BLINDNESS_LEAK), and that decision_type/risk_level are deliberately visible to the blind phase. This is well beyond what the annotations convey. It stops short of describing latency or rate limits, so 4 rather than 5.

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?

Purpose is front-loaded followed by a clearly headed 'BLINDNESS CONTRACT' block, and every sentence carries operational weight rather than filler. The opening sentence is dense with parenthetical enumeration, but the structure keeps it scannable.

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?

With an output schema present, the description needn't document return values, yet it still previews the verdict shape (KEEP | MODIFY | REPLACE | INSUFFICIENT_EVIDENCE). Combined with the blindness contract and cost note, an agent has everything needed to call this correctly for a 9-parameter tool.

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, but the description earns more by explaining the contract governing how fields interact: plan content belongs ONLY in proposed_solution, and leaking it triggers a BLINDNESS_LEAK refusal. That cross-field rule is a semantic layer the per-field schema descriptions state only piecemeal.

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?

The first sentence states a specific verb and resource ('Get ONE independent external review before an expensive decision') and enumerates the qualifying decision categories, so the agent knows exactly what this tool produces. It also names the sibling should_review for the trivial-change case, letting an agent separate the two tools 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 Guidelines5/5

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

Usage is explicit on both sides: call it 'before an expensive decision' enumerated by type, and 'skip it for trivial changes (see should_review)' with a pointer to the gating sibling. It further clarifies review_mode's default and control behavior, leaving nothing to inference about when to invoke.

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

Deploy Server