list_connected_sites

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

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds context about return fields and script installation status. No contradictions, and the description adequately supplements annotations with behavioral specifics.

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?

Description is concise and well-structured with purpose first, then usage guidance, then return format. Minor redundancy (e.g., repeating 'sites') but overall efficient and easy to parse.

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 purpose, usage, and return format. However, fails to explain the account parameter, which is a notable gap given the parameter exists and is undocumented. With output schema present, return details are less critical, but parameter omission hinders completeness.

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?

Parameter 'account' has 0% schema description coverage and the description does not mention or explain it. Although it's optional with default null, the agent receives no guidance on its meaning or usage, failing to add value beyond the schema.

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?

Description clearly states action (list all sites) and resource (connected sites). It specifies the context (Mailchimp account for tracking and pop-up forms) and distinguishes from sibling get_connected_site by indicating when to use each tool.

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?

Explicitly advises to use this tool for discovering site IDs and checking script installation status, and directs to get_connected_site for full single-site records. Provides clear when-to-use and when-not-to-use guidance.

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