update_hosting

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

With no annotations, the description carries the full burden and does so well: it discloses the auth requirement, that version mismatches are reported rather than rejected, that a stale version still applies, that old links and forced subdomain modes remain unchanged, and that the result surfaces a delivery notice. The remaining gap is failure modes (invalid owner token, ineligible resource) and whether the mode change is reversible.

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?

One tight paragraph, front-loaded with scope and exclusions before the mutation semantics. The semicolon-chained clauses about version mismatches and unchanged links are dense but each carries real information, so nothing feels padded.

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 6-parameter mutation tool with no annotations and no output schema, the description covers scope, auth, version-mismatch behavior, and side effects on existing links. It only lacks explicit error/failure conditions and a fuller sense of what the returned delivery notice contains.

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 every parameter is already documented, including expectedVersion's stale-value behavior and the enum meanings for type and deliveryMode. The description's "pass the current hostingVersion when known" and the type/namespace exclusions largely restate what the schema says, adding only modest emphasis rather than new semantics.

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+resource ("Change delivery mode for a NEW publication") and immediately carves out two explicit exclusions (not a site, not a non-public HTML-format page), which is exactly what distinguishes it from sibling publishing tools like publish_site or update_html. An agent can classify the target resource before opening any schema.

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 clear when-to-use conditions (new publication only, exclusions for sites and non-public HTML pages) and a prerequisite (owner token, pass hostingVersion when known). It stops short of naming the sibling tool an agent should use instead for the excluded cases, leaving that inference to the agent.

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