Skip to main content
Glama

get_recovery_signals

Read-only

Check this client's synced Apple Health / Google Fit sleep and resting-heart-rate trend, if any. This is a secondary caution alongside get_client_ai_history and get_platform_rejection_trends, not a hard constraint: if sleepTrend is 'declining' or restingHRTrend is 'elevated', default toward slightly lower volume/intensity this run unless the client's own profile, preferences, or check-ins clearly argue otherwise. If hasData is false, the client has no synced health data yet — ignore this signal entirely and build/adjust normally.

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": {
      "clientId": "<clientId>"
    },
    "name": "get_recovery_signals"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
clientIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses that data may be entirely absent (hasData false), that the data comes from third-party sync and may never have been connected, and that the tool's output is advisory rather than binding. It even names the trend field values ('declining', 'elevated') that drive the interpretation, which the agent could not infer from annotations or 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?

Three sentences, each doing work: what to fetch, how to weigh it, and what to do when empty. The middle sentence is dense but front-loads the actionable rule. Minor slack in the parenthetical list of override sources, but nothing is redundant.

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?

For a two-parameter read-only signal tool with no output schema, the description covers retrieval scope, absence handling, and how to act on the result — enough to invoke and interpret it. It is only incomplete on the days window and on what else the response returns besides the named trend flags.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters, so the description must carry their meaning — but it never mentions clientId or days. The default 14-day window and 1-90 bounds on days are left wholly unexplained, and the phrase 'trend' only loosely implies a time window. This is the definition's largest gap.

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 a specific resource and its origin: this client's synced Apple Health / Google Fit sleep and resting-heart-rate trend. It also positions the tool relative to named siblings (get_client_ai_history, get_platform_rejection_trends), so an agent can place it in the retrieval family. The verb 'Check' is softer than a fetch/list verb, which keeps it just short of a 5.

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 explicitly frames the tool as a secondary caution rather than a hard constraint, states the exact decision rule when sleepTrend is 'declining' or restingHRTrend is 'elevated' (default toward slightly lower volume/intensity), and names the override condition (client profile, preferences, or check-ins arguing otherwise). It also gives the negative case: if hasData is false, ignore the signal and build normally.

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.