Skip to main content
Glama

Read uptime checks

siteChecks
Read-onlyIdempotent

Read whether one owned app is answering its visitors. Every 5 minutes Tofu requests a live app’s home page at its public address, the way a visitor would, and keeps nothing it sends back. Two failed checks in a row open an outage and email the owner once; two good checks in a row close it and, after a “down” email, send one “answering again” email. emailsEnabled is the owner’s switch for those emails. openIncident and recentIncidents are the outages, each with whether the owner was emailed. last_check_failed is one failed check, not an outage yet; unavailable means this Tofu keeps no checks, so nothing here is a reading; an uptime window’s percent is null when it had no check. message is the recorded human-readable explanation of the check state. This read reports Tofu’s recorded visitor-check observations, not an application-level diagnosis. It writes nothing, and another account’s app answers not found.

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": {
      "projectId": "<projectId>"
    },
    "name": "siteChecks"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYes

Output Schema

NameRequiredDescriptionDefault
stateYes
uptimeYes
addressYes
messageYes
availableYes
lastCheckYes
projectIdYes
openIncidentYes
emailsEnabledYes
retentionDaysYes
recentIncidentsYes
checkEveryMinutesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only say readOnly/idempotent/non-destructive/closed-world, and the description goes well beyond them: 5-minute polling of the public home page, the two-failures/two-successes incident state machine, single-email dedup behavior, what emailsEnabled controls, and that unavailable means no checks exist rather than a passing/failing state. It also discloses ownership scoping ('another account's app answers not found'), which annotations cannot express.

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?

Purpose is front-loaded in the first sentence, and the remaining sentences each carry distinct behavioral or field semantics rather than filler. It is dense and list-like in the field enumeration, and some field semantics may overlap the output schema, but nothing is clearly redundant.

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?

For a single-parameter read tool with annotations and an output schema, the description covers the mechanism, edge cases (last_check_failed vs outage, unavailable, null percent), email side effects, and ownership boundary. Anything about the exact return shape can be deferred to 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 0% and the only parameter, projectId, is never described directly; the agent must infer from 'one owned app' and 'another account's app answers not found' that it identifies an owned app with an ownership check. That adds some meaning beyond the uuid format/pattern in the schema, but not a full explanation.

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 opens with a concrete verb and resource: 'Read whether one owned app is answering its visitors,' and later clarifies 'This read reports Tofu's recorded visitor-check observations, not an application-level diagnosis.' That plus 'It writes nothing' separates it from write-side siblings such as setSiteCheckEmails, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states what the data means and that it is not a diagnosis, which implies when to consult it, but gives no explicit 'use this when / use X instead' routing or prerequisites (e.g. how to obtain projectId, or when to prefer the analytics tool). Usage must be inferred from the semantics dump.

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