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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that the funnel is site-configured and results are step-ordered within a single window, which is genuine behavioral context. It says nothing about what happens when no funnel exists or how steps are identified, so it adds moderate rather than rich value beyond 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 sentences, zero filler. The resource and scope are front-loaded, and the disambiguation to onelence_get_performance follows immediately. Nothing is redundant with the title.

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 an output schema present, the description need not explain return values, and annotations cover safety; parameters are fully documented in the schema. What the description supplies — that results are per-step and ordered, and where to go for time-series metrics — is the right level. It could still mention the no-funnel-configured case, which is the one an agent is likely to hit.

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 100% and each parameter carries a detailed description including format and default behavior (start defaults to 30 days before end; site defaults to newest active site). The description's phrase 'for one window' and 'for the site' loosely mirrors those parameters but adds no syntax or constraint detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 concrete resource (the funnel configured for the site in OneLence) and states the scope of the return: visitors who reached each step, in step order, for one window. An agent can distinguish it from a generic performance tool. The only shortfall is that the verb is implicit ('Visitors who reached...' rather than 'Returns visitor counts per funnel step'), so the exact output shape must be inferred.

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 routes the agent elsewhere for related-but-different needs: 'For visitors, conversions and revenue over time use onelence_get_performance.' This is a real alternative with a stated selection condition. It does not cover edge cases such as sites with no funnel configured, so it falls short of a 5.

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