Delx Living Body

Overview Schema Source Related Servers Discussions Admin

Living Body — Ask

living_body_ask

Read-only

Ask a wellness question and receive a synthesized answer with a reasoning trace, pulling relevant data from your detected health connectors. Requires explicit user intent to run.

Instructions

Ask a wellness question; composes detected connectors in parallel and returns a synthesized answer + reasoning trace. Spawns subprocesses — requires explicit_user_intent.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`sources`	No	Restrict composition to a subset of detected connectors. Defaults to all detected.
`question`	Yes	Natural language question about training, recovery, sleep, nutrition or readiness.
`privacy_mode`	No	Passed down to child connectors. Defaults to 'structured'. 'raw' is only honored with explicit_user_intent and is discouraged for routine composition.
`response_format`	No		markdown
`explicit_user_intent`	Yes	Required confirmation that the caller is acting on explicit user intent. living_body_ask spawns multiple wellness MCP subprocesses; agents must not call it speculatively.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`reasoning`	Yes
`confidence`	Yes
`generated_at`	Yes
`sources_used`	Yes
`data_snapshot`	Yes
`recommendation`	Yes
`sources_failed`	Yes
`child_tool_mode`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.7Aug 29, 2026

addedOutput schema / properties / child_tool_mode

Added value: +{
+  "enum": [
+    "context",
+    "daily_summary",
+    "series"
+  ],
+  "type": "string"
+}

First observedv0.3.0Jul 4, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the annotations, the description reveals that the tool composes connectors in parallel, spawns subprocesses, and returns both a synthesized answer and a reasoning trace. These are meaningful behavioral traits an agent would not infer from readOnlyHint/openWorldHint alone. There is no contradiction with the annotations.

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?

Two sentences, roughly 25 words, with the primary verb and resource up front and the critical caveat at the end. Every clause contributes to agent understanding, with no redundancy or filler.

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?

The description covers the core behavior, parallel composition, subprocess side effect, and the intent gate. Since an output schema exists, return values are already specified elsewhere. It does not mention optional parameter defaults like sources defaulting to all detected connectors, but those are documented in the schema, so the gap is minor.

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 80% and each parameter already has its own descriptive text, so the schema carries most of the semantic load. The tool description reinforces that `question` is a natural-language query and `explicit_user_intent` is mandatory, but it does not add new information about sources, privacy_mode, or response_format beyond 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 description states a specific verb-resource pair ('Ask a wellness question') and describes the core mechanism: composing detected connectors in parallel and returning a synthesized answer plus reasoning trace. This clearly distinguishes it from sibling tools like status, capabilities, or data inventory, which serve different purposes.

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 clearly identifies the use case (a wellness question) and the critical precondition that the caller must have explicit user intent ('Spawns subprocesses — requires explicit_user_intent'). It does not explicitly name alternatives or exclusions, but the intent requirement and question-oriented purpose provide strong usage guidance.

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

Deploy Server