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

Adds genuinely useful context beyond the annotations: it names the required scopes ('write scope and analytics.write') and explains the counting semantics (step n+1 only counts when the same person did it after step n within the conversion window). It does not address why destructiveHint=true applies or what a re-save would overwrite, but the annotations already flag the safety profile.

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?

Three sentences, front-loaded with the action and constraints before the semantics. Dense but no filler; each sentence adds a distinct layer (what, how steps count, what scopes are needed).

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 the creation semantics, the nested step structure, and the auth requirement for a destructive mutation with no output schema. It doesn't describe what is returned (e.g. the funnel id) or clarify the destructive/re-save behavior, which would round it out.

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?

With schema coverage at 40%, the description compensates on the hardest parts: 'two to twelve steps' mirrors the minItems/maxItems, 'event name or an exact path' maps to the kind enum, and the utm_source-equals-facebook example plus 'after step n... inside the conversion window' give meaning to filters and windowHours. Only app, name, and description remain undocumented, but they are largely self-evident.

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?

States a specific verb and resource ('Save an ordered funnel') and immediately bounds it with the 'two to twelve steps' constraint. The remaining sentences define what a funnel step is, so an agent can tell this is a create-a-funnel tool. It stops short of naming the read-side siblings (list_funnels, get_funnel_results) for contrast.

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?

'Save' plus 'Requires the write scope' implies this is the mutation path used once you know your funnel steps. But the description never explicitly says when to use this versus list_funnels to read an existing one or get_funnel_results to analyze, so the routing to siblings is left to inference.

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