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

Discloses the two behaviors annotations cannot convey: reusing a name redefines the funnel (overwrite semantics) and `remove: true` deletes it, which matches destructiveHint=true. It also explains the evaluation model (counted from events already stored, returns its last 28 days at once) and that it is free, so an agent knows a save immediately yields results.

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?

The save/overwrite/delete mechanics are correctly front-loaded, but the body is a dense run-on with heavy parenthetical nesting that is harder to parse than it needs to be. The content earns its place; the packaging does not.

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?

Covers step types, ordering semantics, defaults, deletion, and the fact that results are computed immediately from stored events — everything needed to invoke it correctly, especially since no output schema exists. Minor omissions (siteId, the 2-8 step bounds, the 90-day window cap) are left to the schema, which documents them.

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?

Goes well beyond the 67% schema coverage by defining each step type operationally — PAGEVIEW paths with wildcards, EVENT names and the name@/path form that t.js sends with no site code, CTA data-sf values, ENGAGED, REVENUE, CHECKOUT as a return from hosted checkout. It also gives the purpose of `any` (alternate ways to satisfy a step) and `evidence` (file:line) plus the defaults for strict and windowDays.

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?

Opens with a specific verb and resource ("Save a funnel") and immediately narrows the scope to funnels mapped from the site's code, which separates it from funnel_check and goals_save well enough to choose between them. It does not name the siblings directly, so an agent still has to infer that funnel_check is the read-side counterpart.

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?

Gives concrete discovery guidance (use analytics page_flow for top pages, where visitors go next, what they click) and a diagnostic rule of thumb ("a step no one reached is usually a wrong pattern"). It never states when not to use it or points at funnel_check for validation, so the routing is implied rather than explicit.

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