Taste

request_human_approval

Pause your workflow for explicit human approval before executing a high-stakes action. Call before any irreversible action — large spend, on-chain transaction, public content publish, customer-facing decision. Returns approved/denied + reasoning. Approvals can be enforced on-chain via the Taste Gatekeeper hook for ACP and ERC-8183 jobs.

Input Schema

TableJSON Schema

Name	Required	Description
`stakes`	Yes	What kind of risk the action carries. Reversible: undoable. Irreversible: cannot be undone. Financial: moves value. Public: visible externally.
`context`	No	Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.
`timeoutMinutes`	No	Maximum minutes to wait for a human response before returning denied_timeout. Default 30, max 120.
`actionDescription`	Yes	Describe the action awaiting approval. Include numbers (amounts, recipients, URLs) the human needs to see.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`tip`	Yes
`status`	Yes
`message`	Yes
`offering`	Yes
`priceUsdc`	Yes
`sessionId`	Yes

TDQS

A4.8/5.0

Behavior5/5

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

No annotations are provided, so the description carries full burden. It clearly discloses the behavior: pauses workflow, returns approved/denied with reasoning, and mentions on-chain enforceability. This is comprehensive and accurate.

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

Conciseness5/5

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

The description is four sentences with no wasted words. The first sentence front-loads the core purpose, followed by specific usage examples, return value, and advanced feature. Every sentence adds value.

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?

The tool has an output schema (mentioned but not shown), and the description explains return values (approved/denied + reasoning). It also covers enforcement mechanism, which is advanced context. For a tool with 4 parameters and moderate complexity, this is complete.

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

Parameters5/5

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

Schema coverage is 100% with descriptions, but the description adds value beyond schema by advising that actionDescription should include numbers the human needs to see (amounts, recipients, URLs) and that context clarifies intent and constraints. This extra guidance improves usability.

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 description clearly states it pauses workflow for explicit human approval before high-stakes actions. It distinguishes from siblings like ask_a_human and consult_domain_expert by specifying it is for irreversible actions (large spend, on-chain transaction, public content publish, customer-facing decision).

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 provides clear context for when to use the tool: before any irreversible action. It lists concrete examples. However, it does not explicitly mention when not to use it or name alternatives among the siblings, which would strengthen guidance.

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

All Taste tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose, covering different aspects of human expert evaluation: dispute arbitration, domain consultation, content review, certificate verification, etc. Even similar tools like review_content and prepublish_review differ in their focus (facts vs. cultural sensitivity), and order_think_tank_session_30 and _60 only differ by duration, which is natural.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in lowercase with underscores (e.g., arbitrate_dispute, list_offerings, verify_certificate). There is no mixing of conventions or vague verbs, making the naming predictable and easy for an agent to infer functionality.

Tool Count5/5

With 17 tools, the server strikes a good balance—enough to cover a wide range of human expert evaluation tasks without being overwhelming. Each tool serves a specific, justifiable purpose within the domain.

Completeness4/5

The tool set covers core workflows like ordering evaluations, retrieving results, requesting revisions, and verifying certificates. However, there is no explicit tool for ordering an illustration (only revision), which is a minor gap. Overall, the surface is nearly complete for the stated purpose.

Resources

Need Help?