publish_page

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

Annotations only declare destructive/openWorld; the description adds substantial context they cannot carry: the build-host fallback to a source-only publish that 'serves nothing' and returns a warning, the ~10-minute rendering window on preview links, domain reuse semantics on republish, and the credential requirement. It is consistent with destructiveHint=true (it overwrites the live published record) and never contradicts 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?

Front-loaded with the action and its two effects before diving into fallbacks and domain behavior, and every sentence carries real information. It is one dense, deeply nested paragraph rather than cleanly segmented, which costs it the top mark.

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 complex mutating tool with no output schema, the description covers the full lifecycle: what is built, what record is written, what URL is served under each domain case, what happens with no build host or a failed build, and what dry_run returns. Nothing an agent needs to invoke it correctly 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 description coverage is 100%, so the baseline is 3. The description restates the custom_domain omit-vs-'' distinction and the dry_run default that the schema already documents, adding little parameter meaning beyond the structured fields.

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 ('Publishes an existing page') and immediately distinguishes it from sibling mutations like update_page/create_page by naming the two concrete effects: building the rendered app on the build host and creating/updating the published record that public serving reads. An agent knows exactly what this does without opening the 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 operational context: dry_run defaults to true so an agent knows calling it blind does nothing destructive, and it explains the domain-resolution conditions (custom_domain provided / omitted / empty). It stops short of naming alternatives (e.g. render_preview or update_page) or stating when not to publish, so not a 5.

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