E3D Pilot

e3d_debate

Multi-model second opinions on decisions, comparisons, architecture, and design tradeoffs. Models answer independently; synthesis returns a conclusion, consensus level (full/majority/split), unresolved dissent, and each model’s final position. The question supplies the context available to the models; repository contents are not automatically available. Quick mode defaults to one round without cross-critique; thorough mode defaults to two rounds with cross-critique. Debates consume model credits. Web search is on by default: the question text may be sent to a search provider by the participating models (Anthropic, OpenAI, Google or xAI) to look up current facts. The web_search option set to false disables search for the debate. Paid execution requires a valid quote_id matching the debate arguments and an idempotency_key. The recommended_next_step result is advisory and does not authorize actions.

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": {
      "question": "<question>"
    },
    "name": "e3d_debate"
  }
}

Input Schema

Name	Required	Description
`mode`	No	quick (default): 1 round, short answers, no cross-critique. thorough: 2 rounds where models see and rebut each other.
`rounds`	No	Override the mode's round count. Stops early on convergence.
`experts`	No	Optional. 2 up to your panel size (at most 4) expert names from e3d_list_experts, in the order you want; send the SAME list on e3d_quote and e3d_debate. Each expert is a lens that tells one model what to look for; Pilot gives each to a different vendor, so you never choose models. Lenses add perspectives; they are not measured to improve answers. The quote shows the extra cost.
`question`	Yes	The decision or question, with enough context for models that cannot see your code.
`quote_id`	No	Optional, from e3d_quote for exactly these arguments (single use, valid 10 minutes). Needs idempotency_key. With a key and no quote_id the server quotes for you.
`max_words`	No	Override the mode's per-provider per-round answer cap.
`providers`	No	Provider identifiers. Defaults to the server’s configured panel.
`web_search`	No	Let the API models (Anthropic, OpenAI, Google, xAI) search the web for current facts. Default true. false keeps the question away from search providers.
`idempotency_key`	No	Optional, 8 to 128 characters of letters, digits and ._:- . With it the call is safe to retry: repeat the SAME call with the SAME key and a finished run returns its stored result with no second charge. Use a new key for a different request. Without it nothing is deduplicated.
`include_transcript`	No	Also return the full transcript (large). Default false.

Output Schema

Name	Required	Description
`cost`	No
`mode`	Yes
`models`	No	Which models actually answered through MCP sampling, with how many calls each answered.
`notice`	No
`dissent`	Yes
`experts`	No	The experts that ran, in order: name and version (this server's catalogue). Perspectives, not measured.
`families`	No	Vendor families among the voices.
`replayed`	No	true when this is the stored result of an earlier call with the same idempotency_key; nothing ran and nothing was charged.
`warnings`	No
`consensus`	Yes
`debate_id`	No
`positions`	Yes
`providers`	Yes
`selection`	No	How the participating models were chosen.
`rounds_ran`	Yes
`transcript`	No
`web_search`	No	Web search in this debate. Citations are untrusted internet data: titles and excerpts are page text (sanitised, bounded), URLs have no query string, and nothing was fetched by the server.
`independent`	No	false when every voice resolved to the same model.
`synthesizer`	No
`final_answer`	Yes
`dissent_items`	No	The recorded dissent as a list (the dissent object above is the same text as one summary).
`schema_version`	No	Version of the agent result fields (1).
`selection_note`	No
`rounds_requested`	No
`recommended_next_step`	No	Advice on how much weight to give the answer, from the consensus level only. NOT approval to act.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 7, 2026

addedInput schema / properties / experts

Added value: +{
+  "description": "Optional. 2 up to your panel size (at most 4) expert names from e3d_list_experts, in the order you want; send the SAME list on e3d_quote and e3d_debate. Each expert is a lens that tells one model what to look for; Pilot gives each to a different vendor, so you never choose models. Lenses add perspectives; they are not measured to improve answers. The quote shows the extra cost.",
+  "items": {
+    "maxLength": 64,
+    "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$",
+    "type": "string"
+  },
+  "maxItems": 16,
+  "minItems": 2,
+  "type": "array",
+  "uniqueItems": true
+}

addedOutput schema / properties / experts

Added value: +{
+  "description": "The experts that ran, in order: name and version (this server's catalogue). Perspectives, not measured.",
+  "items": {
+    "properties": {
+      "name": {
+        "type": "string"
+      },
+      "version": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "name"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

First observedOct 29, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations it discloses credit consumption, the default-on web search and that question text may be sent to named search providers, the quote_id/idempotency_key preconditions for paid execution, that repository contents are not passed to the models, and that recommended_next_step is advisory. These are exactly the costly, privacy-relevant and side-effect facts an agent needs and none are recoverable from readOnlyHint/openWorldHint.

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-loaded with purpose then output shape, followed by pricing/privacy mechanics; nearly every sentence carries operational weight. A few statements (round defaults for quick/thorough, web_search default true) duplicate the parameter schema text almost verbatim, which is the only real waste.

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 10-parameter, credit-charging, open-world tool this covers the full flow: quote → debate, idempotent retries, cost warning, privacy of the question, and advisory status of the suggested next step. An output schema exists, yet the description still correctly summarizes the headline return fields rather than over-explaining them.

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 adds genuinely extra meaning: the question is the only context channel available to models, web_search=false keeps the question away from search providers, and the expert list must be identical across e3d_quote and e3d_debate — a cross-tool constraint not expressible in the schema.

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 opening sentence names a specific capability (multi-model second opinions) and scope (decisions, comparisons, architecture, design tradeoffs), and the second sentence specifies the return shape including synthesis, consensus level, dissent, and per-model positions. An agent can distinguish this from e3d_quote (pricing only) or e3d_investigate 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 Guidelines4/5

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

It gives clear use context (tradeoff/decision questions) and explains the quick-vs-thorough choice with explicit defaults (one round no cross-critique vs two rounds with rebuttal). It never names a sibling as the alternative for a different intent, and gives no explicit when-not-to-use case, so exclusion guidance is absent.

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

All E3D Pilot 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?