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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the write nature is known. The description enriches this with specific behavioral details: it requires human review, charges 2.5 USD, demands explicit wallet authorization, and enforces content constraints (no invented promises/testimonials/imagery). This goes beyond the schema and annotations, though it does not detail the full workflow or side effects.

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 with zero wasted words. The first sentence leads with the core action and inputs, the second explains the mechanism (bounded planner, deterministic templates), and the third covers constraints and pricing. Every sentence adds distinct information, making it easy to scan and absorb.

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?

The description covers inputs, process, constraints, human review, and cost, but lacks any indication of output format or return value. Since there is no output schema, the agent cannot know what result to expect. It also leaves the payment/signature mechanisms under-specified, which is risky for a tool that explicitly requires wallet authorization.

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 description coverage is 0% and the description does not explain individual parameters beyond vaguely mentioning services and assets. The nested input object's fields like business_name, location, request_url, and the various signature parameters are undefined in both schema and description. For a paid, destructive tool, this is insufficient – the agent is left guessing which parameters are essential and how signatures relate to payment.

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 specific verb ('Create'), a concrete deliverable ('14-day campaign and newsletter'), and explicit input sources ('buyer-supplied services and authorized assets'). The phrase 'evidence-based' and 'bounded planner' differentiate it from generic content creation tools by emphasizing constraint and determinism, setting it apart from siblings like newsletter_draft or social_calendar.

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 context is implied through phrases like 'explicit buyer-supplied services and authorized assets' and 'No invented promises', which suggests when this tool is appropriate (when evidence assets are available). However, it never explicitly names alternatives or states conditions for when not to use this tool, leaving the agent to infer from the many sibling content tools.

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