Skip to main content
Glama

Vayu Breathing

Find a breathing practice for how you feel

find_breathing_practice
Read-onlyIdempotent

Pick the breathing practice that fits how the user feels right now, explain why, and show it in a timer they can start, with one or two alternatives they can switch to. Use it when the user describes a feeling or a need instead of naming a technique: can't sleep, anxious, a panic moment, stressed, overwhelmed, racing thoughts, brain fog, needing to focus, nerves before a big moment, low energy, a midday slump, starting the day, or wanting to unwind. It is a relaxation exercise, not medical treatment; do not use it for chest pain, fainting, severe breathlessness or another emergency. Nothing is saved.

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": {
      "need": "<need>"
    },
    "name": "find_breathing_practice"
  }
}

Input Schema

NameRequiredDescriptionDefault
needYesWhat the user needs. cant_sleep: lying awake, can't fall asleep, winding down for bed. anxious: anxious, nervous, worried, on edge. panic: panicky, heart racing, can't calm down, spiralling. stressed: stressed out, tense, wound up. overwhelmed: overwhelmed, too much at once, under pressure. racing_thoughts: scattered or racing thoughts, can't switch off. foggy: foggy, can't think clearly, need to refocus. focus: focus for work or study, concentrate. big_moment: before a meeting, exam, interview, talk, performance or game. low_energy: tired, sluggish, flat, need a lift. midday_slump: afternoon slump, post-lunch dip. morning_start: starting the day, morning routine. unwind: relax, calm down, decompress after the day.
minutesNoSession length in minutes (1, 2, 3, 5, 10), if the user said how long they have. Leave it out to use the recommended length.
time_of_dayNoThe user's local time of day, if known. Energising options are swapped for calmer ones in the evening and at night.

Output Schema

NameRequiredDescriptionDefault
whyYes
needYes
noteNo
labelYes
practiceYes
alternativesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds genuine context: 'Nothing is saved' clarifies persistence, and 'It is a relaxation exercise, not medical treatment' sets a scope boundary the annotations cannot express. It does not detail failure modes for an invalid need value, which keeps it from a 5.

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 the core action in the first sentence, then the trigger list, then the safety caveat — a sensible order. The long feeling enumeration is functional rather than filler, though it duplicates the enum values already in the schema and could be trimmed slightly.

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?

With an output schema present, the description needn't document return values, and it covers purpose, triggering conditions, safety exclusions and persistence in a compact space. Nothing an agent needs in order to call this correctly is missing.

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% and each enum value already carries a detailed gloss, including the note that energising options are swapped for calmer ones in the evening or at night. The description's feeling list echoes the enum values and adds little new meaning about parameters, so the baseline 3 applies.

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?

Uses a concrete verb ('Pick the breathing practice that fits how the user feels'), states the resource, and describes the output ('show it in a timer they can start, with one or two alternatives they can switch to'). The phrase 'when the user describes a feeling or a need instead of naming a technique' implicitly separates it from explain_breathing_technique and start_breathing_session, so an agent can route correctly without opening the 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 an explicit trigger condition plus a concrete list of user phrasings (can't sleep, panic moment, brain fog, midday slump, etc.), and a clear exclusion: chest pain, fainting, severe breathlessness or other emergencies. Both when-to-use and when-not-to-use are stated, leaving little inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources