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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, and the description adds real context beyond them: the operation is asynchronous, must be polled via get_agent_session, requires a provisioned site, and may execute source edits in a preview. The note that the Replo agent uses connected integrations and normal tools also warns of side effects. It doesn't explain what specifically makes it destructive, which keeps it below a 5.

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 critical facts (create draft, preserve pages, async + poll) are front-loaded, and every sentence is functional. The sentence about the Replo agent using its normal tools and integrations is the most expendable, keeping it from 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?

For a 4-parameter asynchronous mutation with no output schema, the description covers the full agent loop: prerequisites, what to put in instructions, how to poll (get_agent_session), how to iterate on corrections, and how publishing is separated. An agent has everything needed to call it and handle the result correctly.

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 100%, so baseline is 3, but the description adds genuine semantics: instructions should carry copy, layout, product references and design requirements, and sessionId is the continuation handle for corrections with an unchanged target. That is more than the schema alone conveys, though it doesn't clarify the route pattern or the 7500-char limit.

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 opens with a precise verb+resource+scope: "Create a draft page at one route in an existing site," which immediately distinguishes it from edit_site_page and delete_site_page. "Preserve existing pages" further narrows the semantics, so an agent can tell it is additive rather than mutating existing routes.

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?

It names an alternative for the follow-on step ("Use publish_site separately to make changes public") and states the correction path (re-call with the same sessionId and unchanged target), plus the prerequisite that a site must be provisioned. It stops short of explicitly contrasting with edit_site_page/delete_site_page, so it's clear context without full exclusion guidance.

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