Skip to main content
Glama

Audit a lead magnet

audit_lead_magnet
Read-onlyIdempotent

Findings about one lead magnet, derived from its real numbers and its page: where visitors drop off (before the form or in it), sources that convert far below or above the rest, where readers stop, leads who never download, and page problems (no description, no cover image, an unlinked button, a PDF older than its ebook). Each finding carries its evidence, and rules stay silent when there is too little data. Use it to give data-backed advice; it never returns who the leads are.

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": {
      "magnetId": "<magnetId>"
    },
    "name": "audit_lead_magnet"
  }
}

Input Schema

NameRequiredDescriptionDefault
rangeNoWhich UTC days the numbers cover. Default 30d.30d
magnetIdYesFrom list_lead_magnets.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, so safety is covered. The description still adds genuine behavioral context beyond that: findings carry their evidence, rules stay silent when data is thin, and lead identities are excluded. Those are real traits, though the description says nothing about cost, latency, or how sparse results can be in practice.

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?

One dense paragraph that front-loads the finding categories, then closes with the behavioral caveats. Every clause corresponds to a distinct capability, so there is little waste. The long comma-separated enumeration of page problems is slightly heavy but still readable and purposeful.

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?

No output schema exists, so the description carries the return-value burden, and it does: it names the five finding families, states that each finding includes evidence, and warns that some rules will be silent. For a two-parameter read-only diagnostic this is close to complete; only the shape of an individual finding is left vague.

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%, with range documented as UTC days with a 30d default and magnetId documented as coming from list_lead_magnets. The description adds no parameter-level detail at all — no guidance on when to widen the range to 'all' or what a short range does to finding reliability. With the schema fully documented, 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 gives a specific verb-ish framing (diagnostic 'findings') and a specific resource (one lead magnet), then enumerates the concrete finding categories: drop-off points, converting sources, reading stop points, non-downloading leads, and page defects. That is far more informative than a generic 'audit'. It does not name the sibling that returns raw metrics (get_lead_magnet_performance), so the boundary is inferable rather than explicit.

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?

It states the intended use case plainly: 'Use it to give data-backed advice,' which tells the agent this is an interpretation layer rather than a data-fetch. It also sets a negative boundary ('it never returns who the leads are'), implicitly routing identity questions elsewhere. It stops short of naming which sibling to call for raw numbers or per-lead data, so the alternative is not spelled out.

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