2hives: Sleep & Meditation

Find a session

find_sessions

Read-only

Use this when the user wants something to listen to for sleep, relaxing, breathing or focus and has not named a session: an evening wind-down, sleep audio, a nap, a breathing break, focus, a study break, a reset before a meeting or exam, a body scan, gratitude, or nature sounds with a gentle voice. Not for medical questions, emergencies or a crisis. Not for general chat about meditation.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_sessions"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No	What the session is for. Pick from the user's words: sleep (sleep audio, a nap), calm (wind down, before a meeting), breath (breathing), focus (study, work), body (body scan), nature (nature sounds with a voice). Default: calm.	calm
`music`	No	Background music on or off. Default true.
`voice`	No	Voice preference. Default any.	any
`language`	No	Audio language as a BCP-47 code (en, es, pt-BR, fr, it, ja, hi, ko, hu, or any other such as pl). Always pass the language the user writes in. If the language is not available the answer says so and gives the closest live one. hi, ko and hu are beta.
`length_min`	No	Length in minutes, 3 to 60. Default 10 when the user gives none.

Output Schema

Name	Required	Description	Default
`ui`	No
`job`	No
`tap`	No
`url`	No
`host`	No
`lang`	No
`view`	No
`ended`	No
`beacon`	No
`reason`	No
`status`	No
`profile`	No
`ai_voice`	No
`language`	No
`manifest`	No
`sessions`	No
`help_lines`	No
`queue_line`	No
`session_id`	No
`ai_voice_label`	No
`language_changed_from`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnly, non-destructive, closed-world behavior, so the safety profile needs no restating. The description adds genuine behavioral context about language availability and the fallback to the closest live language, but says nothing about what is returned or how recommendations are ranked. Useful additions, but thin given a read-only tool with an output schema.

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?

The trigger condition is front-loaded in the first clause, followed by use-case examples and then exclusions. The long enumeration of scenarios is somewhat list-heavy, but each item clarifies an otherwise ambiguous 'calm' vs 'sleep' vs 'focus' routing decision, so it largely earns its space.

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?

With five optional parameters, full schema coverage, annotations, and an output schema, the description supplies the missing piece an agent needs: intent routing and hard exclusions. What remains unsaid is the return granularity and whether it returns multiple candidates, which is partially mitigated by the output schema.

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 coverage is 100%, with enums and defaults already documented for kind, music, voice, language, and length_min. The description's scenario list roughly maps to the kind enum values but adds no syntax, unit, or boundary detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (a session) and the scenario it serves, enumerating concrete targets like evening wind-down, sleep audio, breathing break, focus, body scan, and nature sounds. It is clear the tool produces a playable/listenable session, though it never states the return shape explicitly (one session vs. a list), which is partly covered by the output schema. Sibling differentiation is only implied via 'has not named a session'.

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?

It front-loads the triggering condition ('when the user wants something to listen to ... and has not named a session') and then gives explicit exclusions: not for medical questions, emergencies, crisis, or general chat about meditation. Both the when and the when-not are stated, leaving little to inference.

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

All 2hives: Sleep & Meditation 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?