Skip to main content
Glama

Check that the tools still work

health_check
Read-onlyIdempotent

Run live checks against a library's website to confirm every Stacks tool still works and report exactly what broke if the site changed. Use it when a tool returns SITE_CHANGED.

Instructions

Run live checks against a library's website to confirm every Stacks tool still works, and report exactly what broke if the site changed. Checks page landmarks (TinyFish Fetch) and the data contract of each tool using known-good queries (TinyFish Browser). Set deep to also start a TinyFish Agent that inspects a failing page and explains what changed. Takes about 20 to 40 seconds. Run this when a tool returns SITE_CHANGED.

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": "health_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
deepNoIf a check fails, start an Agent run to diagnose the failing page (result via get_job_result).
libraryNoLibrary system id such as "tpl" (Toronto), "vpl" (Vancouver), "chipublib" (Chicago). Get it from find_library. A city or library name also works.

Output Schema

NameRequiredDescriptionDefault
checksYes
healthyYesFalse if any check failed.
libraryYes
summaryYes
checked_atYes
tinyfish_callsYesTinyFish calls this check made, by endpoint.
diagnosis_errorYesWhy the Agent diagnosis could not be started, if it could not.
diagnosis_job_idYesPass to get_job_result for the Agent's diagnosis of the failing page.
platform_versionYesVersion of the library platform seen on the site now.
verified_platform_versionYesPlatform version these tools were last verified against.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.3

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely new context: a 20-40 second runtime and what the checks actually inspect (page landmarks via Fetch, data contracts via Browser). It stops short of stating in the description that the deep Agent run is asynchronous and must be polled via get_job_result — that detail lives only in the schema text.

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?

Four tight sentences, front-loaded with purpose, then mechanism, then the deep escalation, then the runtime and trigger. Every sentence carries information an agent would otherwise have to infer.

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?

An output schema exists, so return values need no explanation here. With annotations, full schema coverage, and the failure-signal trigger all present, an agent has everything needed to decide when to call this and how to interpret the request.

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%, so the baseline is 3. The description restates what deep does and implies that library scopes the checks to a site, but adds no format or syntax detail beyond the schema's own examples of library ids.

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: 'Run live checks against a library's website to confirm every Stacks tool still works, and report exactly what broke.' This is clearly a diagnostics/smoke-test tool, distinguishable from siblings like check_availability or search_catalog, which operate on library data rather than on the tool surface itself.

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?

'Run this when a tool returns SITE_CHANGED' gives an explicit, unambiguous trigger condition, and the deep flag's escalation path is spelled out. The only minor gap is the absence of a 'do not run routinely' exclusion, but the trigger framing makes the intent clear enough for correct selection.

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