Entalpa Requirements MCP

Suggestions Review

suggestions_review

Read-onlyIdempotent

Show one run's saved suggestions in an interactive review where the user accepts or declines each proposed change, shown beside what it would change. Pass the batch_id of a run's saved_suggestions; without it, the newest batch waiting for review is shown. The user sees the changes in the view, so the result only counts them: do not list them again in your reply. What the user decides in the view is applied from there; call suggestions_accept or suggestions_reject only for decisions the user states in chat. The view shares those decisions as its context: when the user refers to them, read that context before answering (some hosts attach it to the message, others offer a tool that reads an app's or widget's context), or check the items with suggestions_list. If your client cannot display the view, give the user review_url, which opens the same review in the Entalpa app. Uses no AI and no credits.

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": {
      "project_id": "<project_id>"
    },
    "name": "suggestions_review"
  }
}

Input Schema

Name	Required	Description	Default
`batch_id`	No	Suggestion batch UUID, from a run's saved_suggestions or from suggestions_list. The newest batch waiting for review when omitted.
`project_id`	Yes	Project UUID (database id).

Output Schema

Name	Required	Description
`shown`	Yes	Items the view shows, whatever their status; 0 when nothing waits for review.
`batch_id`	No	Suggestion batch UUID of the review shown.
`statuses`	No	How many of them are in each status: pending and stale ones wait for review.
`operation`	No
`review_url`	No	Opens the same review in the Entalpa app.
`other_batches_waiting`	Yes	Other batches with items waiting for review. suggestions_list gives their ids.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnly/idempotent/no-open-world, but the description adds real operational context: the result merely counts the changes rather than listing them, decisions are applied from inside the view, the view exposes its decisions as context that should be read before answering, and the call costs no AI or credits. It also handles the non-rendering-client fallback, which no annotation conveys. The 'decisions applied from the view' wording sits slightly in tension with readOnlyHint, but the description is careful to say the accept/reject application is not performed by this call.

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?

Front-loads what the tool does, then tacks on the batch_id rule, the 'don't re-list results' instruction, the chat-vs-view routing, and the review_url fallback — every sentence carries operational weight. It is a dense block of six sentences in one paragraph, though, and would read better split into usage and behavior lines.

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?

An output schema exists, so return values need no prose. Given the tool renders an interactive surface, the description covers the pieces an agent actually needs: default batch selection, who applies decisions, how to recover the view's decisions as context, the non-UI fallback, and the cost profile.

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 both parameters are already documented, and the prose largely restates the batch_id default ('newest batch waiting for review'). It adds the provenance hint (batch_id comes from a run's saved_suggestions) but nothing about format or validation beyond the schema. Baseline 3 is correct.

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 — showing one run's saved suggestions in an interactive accept/decline review alongside a preview of the affected content — and implicitly separates itself from suggestions_list (read items) and suggestions_accept/reject (apply decisions). An agent can tell this apart from every sibling without opening a 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?

Gives explicit routing: pass batch_id from a run's saved_suggestions, otherwise the newest pending batch is shown; call suggestions_accept or suggestions_reject only for decisions the user states in chat, not for decisions made in the view; and if the client can't render the view, hand the user review_url. Both the when and the when-not are stated.

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

All Entalpa Requirements MCP 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.

Resources

Need Help?