Skip to main content
Glama

Tomorrow Central: Cloud Cost Sentinel

Can the tracking be trusted

webops_measurement
Read-onlyIdempotent

Can a window's Analytics be trusted? Checks freshness, missing days, event mix, one page suddenly holding an event, conversions without visits, "(not set)", sudden source shifts; each ok, doubt or unknown, and a verdict. Another organization's or an unconnected site answers not found. Read-only.

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": {
      "domain": "<domain>"
    },
    "name": "webops_measurement"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoWindow length in whole weeks of days (7, 14, … 182; default 28), ending on the latest day with data, against the same number of days before.
domainYes
after_toNoLast day of the later window (same length as the earlier one).
before_toNoLast day of the earlier window.
after_fromNoFirst day of the later window.
before_fromNoInstead of days: first day of the earlier window (give all four).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior: each check resolves to ok/doubt/unknown with an overall verdict, and out-of-scope domains (another organization's or an unconnected site) return not found rather than an error. It does not explain cost, runtime, thresholds for doubt vs unknown, or what the verdict values are.

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?

Compact: a lead question, a semicolon-delimited list of checks with their outcome vocabulary, a scope caveat, and a read-only marker. The check list is dense but every item names a distinct failure mode, so little is wasted; a bulleted breakdown would be more scannable than the semicolon run-on.

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?

With six parameters (one required), 83% schema coverage and no output schema, the definition supplies the missing return contract in prose – per-check ok/doubt/unknown plus a verdict – and covers the important edge case of domains the caller cannot access. What remains thin is how the window parameters interact and what the verdict scale looks like, which the agent must infer.

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 83%, so the schema already carries most parameter meaning (window length in whole weeks, the four explicit date bounds, mutual exclusivity of days vs dates). The description adds nothing about parameters – not the week multiple constraint, not the day range 7-182, not how the two-window comparison is chosen. Baseline 3 applies.

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 states a specific resource and operation: an audit of a domain's Analytics data covering freshness, missing days, event mix, anomalous page events, conversions without visits, "(not set)" and source shifts, ending in a verdict. It is clearly a data-quality/trust check rather than a metrics report, though the framing as a question ("Can a window's Analytics be trusted?") makes the verb implicit rather than stated up front. It does not name the closest-sounding sibling (webops_analytics_health), so differentiation is only partial.

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?

Usage is implied – you run it to decide whether the numbers in a window are trustworthy before relying on other analytics tools – but the description never says when to prefer this over siblings such as webops_analytics_health or webops_compare. No prerequisites or exclusion conditions are given beyond the not-found behavior for other orgs' or unconnected sites.

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