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

Annotations already declare readOnly=false, destructive=false, and idempotent=false, so the safety profile is covered. The description adds genuine context beyond that: the return content (preview/edit URLs) and a permission gate (draftEditorUrl only when the site grants AI agents Full access). It still doesn't say what the session mutates, how long it lives, or whether it must be discarded.

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 short sentences, front-loaded with the action and the return value. The only waste is the unresolvable "(see linkGuidance)" pointer, which costs a clause without conveying information.

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 and four parameters, the description should carry more: the shape of the returned URLs is hand-waved via an external, undefined reference, and session lifecycle (creation, reuse, discard via discard_drafts) is absent. For a session-establishing tool this leaves the agent guessing about next steps.

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 75%, with site, context, and guestToken already documented in-schema; the description's contribution is limited to clarifying that path defaults to '/'. It adds no format or constraint detail for path or for how site/path interact in a session.

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?

"Open a draft session" states a verb and resource, but "draft session" is never defined, so an agent cannot tell what state change this creates or how it relates to siblings like edit_page, apply_changeset, or discard_drafts. It does concretely say it returns preview/edit URLs, which adds some specificity.

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?

There is no guidance on when to open a session versus editing directly with edit_page/put_content, nor when to end one. The only routing hints are incidental: the guestToken parameter description points at start_site and claim_site, and the parenthetical "see linkGuidance" is not resolvable from anything in the tool definition.

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