Skip to main content
Glama
Sign In

Sigwren

by com.sigwren
OverviewDiscussionsAdmin

A fitness test to run, and what to send back

get_fitness_test
Read-onlyIdempotent

A fitness test a runner can do on their own, from Sigwren: Metabolic Lite (two 20-second sprints and two 6-minute efforts — threshold pace, LT1, VO₂max, VLamax, fat burning and the training zones they set) or a 20- or 30-minute threshold time trial (threshold heart rate and pace, and the zones they set). Use it for "how fit am I", "find my threshold", "set my training zones", "a test I can run". Pass test (metabolic_lite, threshold_20, threshold_30), or leave it out for the list and the default. It returns the session step by step with each step's length and its effort on a 0–10 scale (RPE) in words — tests have no pace to hold, because they are finding it — what the runner needs (a GPS watch; a chest heart-rate strap if they have one), and exactly which numbers to read off the watch afterwards for each effort. The result then comes one of two ways: get_test_upload_link gives a page where the runner uploads the recording (the better way: Sigwren measures the efforts itself), or work_out_my_test takes the numbers they read off the watch. It needs no account and knows nothing about the person.

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": "get_fitness_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
testNoWhich test: metabolic_lite (the default — threshold pace, LT1, VO₂max, VLamax and fat burning), threshold_20 (a 20-minute time trial — threshold heart rate and pace) or threshold_30 (a 30-minute time trial — the same, for people who prefer the longer one). Leave it out for the list and the default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Goes well past the annotations: discloses the response shape (step-by-step session with step length and verbal RPE on a 0–10 scale), the rationale ('tests have no pace to hold, because they are finding it'), equipment prerequisites (GPS watch, chest strap), which numbers to read off the watch, and the privacy stance ('needs no account and knows nothing about the person'). That is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose, which is good, but the body is a dense run-on packed with em-dash parentheticals listing metrics, equipment, and result paths. Much of the submission-path detail duplicates what get_test_upload_link and work_out_my_test should own, so not every clause earns its place here.

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 no output schema and only one optional parameter, the description fully covers what an agent needs: what is returned, what the runner needs, what to do with the result, and both downstream routes. Nothing material is missing for correct invocation.

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 the single 'test' parameter's enum-like values are already spelled out in the schema, including the default. The description largely restates those choices plus the 'leave it out for the list and the default' behavior, adding no syntax or format detail beyond the structured field. 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?

States a specific verb and resource ('a fitness test a runner can do on their own, from Sigwren') and enumerates the exact variants (Metabolic Lite, 20- or 30-minute threshold TT) with what each measures. It also names the two sibling tools that consume the result (get_test_upload_link, work_out_my_test), so an agent can place it in the workflow 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?

Gives concrete trigger phrases ('how fit am I', 'find my threshold', 'set my training zones', 'a test I can run') and explains the branching after the call: upload the recording vs. enter watch numbers by hand, with a stated preference ('the better way'). It stops short of any explicit when-not-to-use case relative to siblings like get_single_workout or get_test_result.

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

All Sigwren toolsInspect
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