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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is partly covered. The description still adds real value beyond them: the auth requirement (token from first publish, or Authorization: Bearer), the merge/replace distinction, and the return shape with a bumped version. It doesn't say whether omitted files are deleted in non-merge mode, which is precisely the destructive question the annotation raises.

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?

Two tight sentences with zero filler; the core replace-vs-merge semantics and the prerequisite token lead, and the return behavior trails. Every clause carries information an agent needs.

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?

A destructive 5-parameter mutation with no output schema and nested file objects; the description covers the precondition, the destructive/replaceive nature, and points to publish_site's shape for the return. It is nearly complete, though the exact fate of files not included under a non-merge update remains unstated.

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 schema already documents slug, files, merge, token and spa. The description restates the merge semantics already present in the schema's own description ('Keep existing files and add/overwrite only these paths') without adding format or syntax detail beyond it. Baseline 3 is correct when the schema does the heavy lifting.

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 (replace/add) and resource (the files of a slug you already own), and the merge=true qualifier immediately distinguishes the additive case from the replacement case. An agent can tell this apart from publish_site (which creates a new slug) without opening either 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?

The phrase 'a slug you already own' plus 'Requires the token from the first publish' establishes the precondition for using this tool versus publish_site, which is clear context. It stops short of naming publish_site as the alternative for new slugs or stating when-not to use it, so it earns a 4 rather than 5.

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