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

Annotations declare destructiveHint=true and non-idempotent, but the description goes further: it says precisely what is destroyed (pages, theme, header and footer), that the work must be redone afterwards (copy and photos), and that the live URL is unaffected because the result is still a draft. It adds post-call behavior too — share `url`, relay `next_step`, never claim it is live.

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?

Front-loaded with the action, then mode-by-mode breakdown, then the post-call instruction — a clean structure. A few clauses (the owner's "not my style" quote, the repeated reminder to redo copy and photos) are slightly padded, but nothing is redundant with the schema.

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 destructive, nested-payload mutation with no output schema, the description covers draft-vs-live semantics, the three payload shapes, consent, and the follow-up agent script; the stale-write guard lives in the schema text. Nothing an agent needs to invoke this safely is missing.

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 the baseline is 3; the description earns above it by explaining the semantic effect of each mode argument (template_slug rewrites the same site rather than creating a new one; fixture replaces everything; page_updates touches only listed page trees). It does not add detail on expected_draft_updated_at or theme combination beyond what the schema already states.

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?

States a specific verb and resource ("Replace an existing site's DRAFT") and then enumerates the three mutually exclusive modes. An agent can distinguish this from sibling patch_fixture, create_site_from_template, update_page, and set_theme from the text alone.

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?

Gives explicit selection conditions per mode (template_slug = owner wants a different design, fixture = replacement you composed, page_updates = only listed pages) and an exclusion rule: "never build a second site for a switch." It also states the consent prerequisite ("Do it only on the owner's yes"), which is exactly the kind of routing an agent needs.

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