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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the remaining burden is low. The description adds a genuinely non-obvious behavior not present in the schema: filters are scoped to the first funnel step only, which materially changes how a caller interprets every filter parameter. It does not mention auth needs or rate limits, but those are not required given the annotations.

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?

Two tightly written sentences with the returned metrics front-loaded, followed by a short endpoint reference. Nothing is padded, though the raw GET path adds little for an agent that already has the tool binding and the definition is arguably very sparse for a 29-parameter tool.

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?

With no output schema, the description usefully enumerates the three returned measures instead of leaving the return shape unknown. Given the 100% schema coverage and annotations, the main remaining gap is the absence of any guidance on how this differs from related statistics endpoints, which is minor for a tool whose resource is unique among its siblings.

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?

Schema description coverage is 100% across 29 parameters, so the baseline is 3 and the schema does the heavy lifting. The description adds meaning the schema cannot: that all filter parameters are applied to the first step rather than the whole funnel, which is a semantic constraint on how the filters should be used. That is a modest but real increment over the schema.

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 names a specific verb/resource pair (visitors per funnel step) and enumerates the returned metrics (visitors, share of the first step, drop-off between steps). No sibling tool (get_overview, get_totals, get_growth) produces funnel-step data, so an agent can disambiguate without opening any schema.

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 implied by the resource (funnel analysis over a period) but there is no explicit when-to-use vs when-not, no statement of prerequisites, and no routing to alternatives such as pirsch_list_funnels for obtaining the funnel_id. The one useful usage note, 'The filter applies to the first step', is a caveat rather than guidance on tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.