Start here: understand the request

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with a pure-analysis tool. It adds genuinely useful behavior beyond the annotations: it surfaces assumptions, caps blocking questions at 3, never blocks on them, and hands off prefilled arguments — all things the annotations cannot express. Minor gap: it never says whether anything is persisted or how large the prefilled payload is.

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 imperative 'Call this FIRST' is front-loaded, and every clause maps to a real output or rule rather than filler. The single long enumeration sentence is dense but each listed artifact is distinct; it could be split for scanability, which keeps it off a 5.

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 carries the return-value burden and does so by enumerating the response sections, and it clarifies downstream handoff via prefilled arguments for the next tools. Slightly short of complete because the 'events that matter for this audience' and 'compliance notes' are not given scope or size, and the handoff format is unspecified.

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 57%, and the description compensates by naming the semantic dimensions it extracts (niche, product, platforms, regions, currency, offer, deadline) and by noting that platforms and regions are accepted in any spelling or format. The fuzzy-tolerance rule is information the schema, whose platform descriptions list aliases but not the tolerance guarantee, does not fully convey.

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 states a concrete role — an intake/parse step that takes the user's raw request and returns a structured understanding plus routing artifacts. It enumerates exactly what comes back (niche, platforms, regions, events, compliance, landing page direction, prefilled args for next tools), which makes it unmistakable against siblings like event_calendar or content_plan.

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?

"Call this FIRST with whatever the user wrote, even if vague or misspelled" is an explicit ordering constraint plus an input-quality rule, and the example phrase removes any doubt about what to pass. It also resolves the follow-up behavior: questions are never blocking, so the agent knows to ask at most 3 and continue with defaults rather than halt.

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