Identify why a traffic spike occurred by ranking referrers, UTM sources, landing pages, and custom events above baseline, with lift, share, and annotations from the preceding 24h.
Ranked causes for one spike: which referrers/UTM sources, landing pages and custom events rose above baseline (with lift, % and share of the spike), plus annotations (deploys, posts, emails) in the preceding 24h.
| Name | Required | Description | Default |
|---|---|---|---|
| spike_id | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the analytic output shape (ranked causes with lift, % and share) and the time window examined (annotations in the preceding 24h). It doesn't state read-only status or failure modes for an invalid spike_id, but the read-analysis nature is evident.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense sentence, front-loaded with the core purpose ('Ranked causes for one spike') followed by the evidence categories and time window. No filler, though the enumeration is long.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter read tool with no output schema and no annotations, the description is fairly complete: it explains what the output contains and the 24h window. The main missing piece is how spike_id is sourced and the absence of a link to find_traffic_spikes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single spike_id parameter has 0% schema description coverage, so the description must compensate. It implies spike_id identifies 'one spike' but never explains the ID format or where to obtain it, leaving a clear gap for the only required parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific resource (one spike) and what it returns (ranked causes: referrers/UTM, landing pages, custom events, plus annotations). It's clear an agent can tell this apart from a discovery tool like find_traffic_spikes, though it never names that sibling explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: the tool operates on a single spike_id, which suggests it's called after a spike is identified, but no when-to-use, when-not, or alternative tool is named. An agent must infer that spike_id comes from find_traffic_spikes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.