create_funnel

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

With no annotations, the description carries the full burden, and it does add real behavioral context: it returns the funnel with its first results, and visitors are matched within a single UTC day (a meaningful analysis constraint). It does not disclose permissions/auth requirements, whether re-creating a funnel with an existing name overwrites or errors, or any idempotency semantics for this write operation.

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?

Front-loaded with the core action ('Save a funnel'), followed by the domain definition, the step grammar, the return behavior, and the matching constraint. Dense but each clause earns its place; no filler.

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?

No output schema exists, and the description fills that gap by stating it returns the funnel with first results. For a 3-param write tool the calling-critical knowledge (step format, count limits, matching window) is present; only mutation semantics such as permissions and name-uniqueness behavior are absent.

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 67%, but the critical gap is the `steps` array, whose items have no schema description at all. The description compensates well, defining the '/'-prefix page rule, the trailing-'*' prefix-match rule, and the fallback custom-event interpretation, plus the 2-8 count matching the schema's min/max. The `range` and `name` semantics remain schema-driven.

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 gives a specific verb+resource ('Save a funnel') and goes further by defining what a funnel actually is (an ordered list of 2-8 steps visitors move through), which is unusually informative. It does not explicitly distinguish itself from siblings like get_funnel or delete_funnel, but 'Save' vs 'get'/'delete' is reasonably self-evident.

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 agent can infer this is the write path for funnels from 'Save a funnel,' and the valid step grammar is spelled out. There is no explicit when-to-use/when-not guidance and no reference to the get_funnel/delete_funnel alternatives that share the resource.

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