list_sites

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds behavioral context: it returns every site in the workspace (scope), includes specific fields, and notes the call is cheap with no events touched. This enhances transparency, though it does not discuss rate limits or authentication needs, which are less critical given the annotations.

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 description is three sentences plus a short cost note, each sentence adding distinct value: example queries, return fields, usage guidance, and performance hint. It is front-loaded with the most critical information and contains no filler. Every sentence earns its place, making it highly concise and well-structured.

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?

Given the tool's simplicity, the description covers all essential aspects: purpose, return shape, how to use output, and cost. Annotations provide safety and idempotency, schema covers the parameter, and the output schema exists (though not shown). The description does not leave obvious gaps for an agent to misuse this tool.

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 100%, and the schema already explains the tag parameter clearly ('Optional tag name to filter by. Omit to list every site in the workspace.'). The description adds only a slight nuance ('narrows to one group'), which provides minimal extra meaning. With high schema coverage, the baseline is 3, and the description does not significantly improve parameter understanding.

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 starts with explicit example queries ('what sites do I have in Gizmo?', 'list my sites', etc.) and clearly states the tool returns every site in the workspace with specific fields (id, domain, createdAt, ignored status). It differentiates from siblings by emphasizing that it lists all sites with an optional tag filter, and provides a post-usage instruction (using returned site.id for other tools). This makes the purpose highly specific and actionable.

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?

The description advises to 'ANSWER FIRST' for listing queries, indicating primary usage. It explains the optional tag filter and recommends using the returned site.id for other tools. It also notes the call is cheap and touches no events. However, it does not explicitly mention when not to use it or contrast with sibling tools like 'filter_sites_by_tag' for more complex filtering. The guidance is clear but could be more comprehensive about alternatives.

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