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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false, so the safety profile is covered; the description adds real behavior beyond that: safety-check gating, preview-by-default, unlisted-page/claim-token mechanics, and the 3 MB cap. It does not say what happens to the previous live version on update (though the rollback/versions siblings imply retention), which keeps it short of 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?

Three dense sentences, front-loaded with purpose before branching on auth state. The telegraphic 'Signed in:'/'Not signed in:' fragments are efficient rather than padded, though the last sentence stacks two update paths and slightly taxes parsing.

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 14-parameter, nested-object, open-world publish tool with an output schema present, the description covers the auth/preview/live branching and file limits well. Return values are correctly left to the output schema, but the file-exclusion rules (velven.json, dotfiles, node_modules) live only in the schema text, not the prose.

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 per-field baseline is 3; the description goes further by giving cross-parameter rules the schema cannot express (prod is signed-in only, title/type/devices required only for a new space, space vs claim selecting the update path). That relational guidance is genuine added value.

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?

Opens with a specific verb+resource+target ('Publish a browser game, world, tool or wonder on Velven's hosting') and immediately bounds it ('from one HTML page or a small set of files (3 MB in all)'). It also covers the update path (space/claim), so an agent can distinguish it from siblings like versions or rollback without 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?

Explicitly partitions usage: signed-in yields a private preview unless prod:true, unsigned-in yields an unlisted page and a claim token; a new space requires title/type/devices, while updates pass space (signed in) or claim (not signed in). This is exactly the when/when-not routing an agent needs, with no alternative left to inference.

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