Skip to main content
Glama

Read one number by day

metrics_series
Read-only

Reads one business-wide number day by day over the last days, every channel added together: { metric, sources (every source that has measured it), series ([{date, value}], only the days something was measured: a missing day is unknown, never zero), total, level }. One source counts where several measure the same number (Stripe before Marsell's own app for money and subscriptions, else the one read most recently), so sources are never added together. total is the span's sum for a count, and the last measured day's value for a level (level true); null when nothing was measured. Use it for a trend; a piece of work's own results are outcomes_summary, and what is not counted yet and why is in situation_read.

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": {
      "metric": "<metric>",
      "days": "<days>"
    },
    "name": "metrics_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysYesThe span, in days ending today (30 for a month, 90 for a quarter).
metricYesThe number. Counts of each day: visits, sessions_by_source (visits split by where they came from), signups, orders, revenue_cents (money taken, in cents), spend_cents (ad spend, in cents), reach, impressions, engagement, clicks, replies, mentions, citations (AI assistants' answers citing the business), backlinks, posts_published, clips_live (creators' clips that went live), accounts (new customer accounts in the business's own app), activations, new_subscriptions, cancelled_subscriptions, customers (new at the payment provider), booked_calls, video_views (the channel's views that day), uploads. Levels, the standing value on each day: indexed_pages, subscriptions (paying), mrr_cents (monthly recurring revenue, in cents), trials, followers, video_views_total, stars, forks, open_issues, release_downloads (the latest release), downloads (every release since the first).
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / days / maximum
      Removed value: -9007199254740991
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With readOnlyHint already covering the safety profile, the description adds substantive behavior the annotations cannot convey: the series is sparse and a missing day is "unknown, never zero", sources are deduplicated (Stripe preferred over Marsell's own app for money and subscriptions, else most recently read) and never summed, and total means a span sum for counts but the last day's value for levels, null when nothing was measured. These are exactly the traps an agent would otherwise fall into.

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?

Front-loaded with what it reads, then the return shape, then sourcing rules, then the routing sentence to siblings. The parenthetical clauses are dense and somewhat run-on, but with no output schema most of the return-shape detail earns its place.

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?

No output schema exists, and the definition compensates by spelling out the exact response keys (metric, sources, series of date/value, total, level) plus their edge-case semantics. For a three-parameter read tool with a tricky aggregation model, nothing an agent needs before calling appears to be missing.

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 100% and the enum descriptions already enumerate every count and every level in detail, so the description largely restates metric semantics rather than extending them. It does reinforce the counts-vs-levels split that matters for interpreting the result, but adds no new constraint on days or project.

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?

"Reads one business-wide number day by day ... every channel added together" states a specific verb, resource, granularity, and aggregation scope. It immediately tells an agent this is a single-metric time series with cross-channel consolidation, which is distinct from a per-project outcomes read.

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?

"Use it for a trend" gives positive guidance, and it explicitly routes two adjacent needs elsewhere: a piece of work's own results to outcomes_summary, and what is not counted yet to situation_read. It does not state negative cases for the remaining sibling series_* readers, so it stops short of a full when/when-not map.

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.