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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered structurally. The description adds value beyond that by disclosing the computed outputs (reached count, share of first/previous step, lost count, biggest drop) and the fact that an empty argument set fans out over all saved funnels — a behavior an agent would otherwise have to guess.

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 sentences, zero filler. The purpose leads, the metric enumeration follows, and the invocation modes close — a well front-loaded structure where every clause carries information.

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 correctly takes on the burden of describing the return shape, and it does so per-metric. Defaults for range and domain live in the schema. What is missing is precedence/conflict behavior when id, name and steps are combined, and any hint about error handling for invalid step paths.

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 coverage is only 60%, and the two undocumented-in-schema params (id, name) are the ones the description clarifies by tying them to the saved-funnel retrieval mode. It also explains the saved-vs-unsaved distinction for steps, which the schema does not. The remaining gap is the interaction when id/name and steps are both supplied.

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 headline 'Where visitors drop off' plus 'Shows, for each step, how many visitors reached it...' gives a specific verb+resource and even enumerates the computed metrics. The resource (funnel) is inherently distinct from every sibling in the list (top_pages, query_visits, get_timeseries), so an agent can route here without ambiguity.

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?

It explicitly defines the three invocation modes — pass name/id for a saved funnel, steps for an unsaved one, or nothing for all saved funnels — which is real when-to-use guidance. It does not, however, contrast this tool against adjacent analytics siblings like query_visits or get_overview, so the alternative-selection half of the guidance is missing.

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